© 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. 58354
    Prev
    Next
    INDEX
    Explanations

    spect

    np_max-act · gemini-2.0-flash

    analytical methods for detecting specific compounds in biological samples.

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

    The neuron responds to references to analytical instrumentation methods—especially chromatography and mass spectrometry terms.

    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
     zahl
    -0.07
    .Users
    -0.07
    .jobs
    -0.07
     elde
    -0.07
    宝
    -0.07
    zek
    -0.07
     overlaps
    -0.07
    De
    -0.07
    engo
    -0.07
    _ot
    -0.07
    POSITIVE LOGITS
    ウト
    0.06
    ються
    0.06
    Select
    0.06
    уються
    0.06
     приступ
    0.06
     Sport
    0.06
    خصوص
    0.06
    _REALTYPE
    0.06
    (ct
    0.06
     acceptable
    0.06
    Activations Density 0.002%

    No Known Activations