© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 101574
    Prev
    Next
    INDEX
    Explanations

    PV

    np_max-act · gemini-2.0-flash

    words and phrases related to receptor signaling and its impact on various physiological processes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects mentions of TRPV (Transient Receptor Potential Vanilloid) channel names with their subtype numbers (e.g. TRPV1, TRPV4).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CString
    -0.07
    Mono
    -0.07
    .AUTO
    -0.07
     etree
    -0.06
    _reservation
    -0.06
    _BASIC
    -0.06
    ointment
    -0.06
    #####↵
    -0.06
     ситуации
    -0.06
     şu
    -0.06
    POSITIVE LOGITS
     disastrous
    0.06
    arms
    0.06
     signific
    0.06
     disgr
    0.06
    ripple
    0.06
     compar
    0.06
     Listen
    0.06
    ids
    0.06
     zv
    0.06
     struggling
    0.06
    Activations Density 0.003%

    No Known Activations