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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12450
    Prev
    Next
    INDEX
    Explanations

    /detail

    np_max-act · gemini-2.0-flash

    technical terms related to software libraries and programming constructs.

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

    This neuron activates on occurrences of “detail” in include‐path tokens (i.e. file paths that contain a “detail” directory).

    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
     Chamber
    -0.06
    mandatory
    -0.06
    NotSupportedException
    -0.06
    _LOGIN
    -0.06
    Enabled
    -0.06
     Plants
    -0.06
     HPV
    -0.06
     powered
    -0.06
     đảm
    -0.06
     тв
    -0.06
    POSITIVE LOGITS
     уча
    0.08
    etti
    0.07
     Seymour
    0.07
    quisitions
    0.07
    ARDS
    0.07
    važ
    0.07
    都
    0.06
    (tv
    0.06
    ，都
    0.06
    @m
    0.06
    Activations Density 0.001%

    No Known Activations