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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44259
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron is mainly responding to inline documentation “<code>…</code>” markers, i.e. the literal code‐tag tokens in comments.

    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
    нь
    -0.07
     своей
    -0.07
    ablytyped
    -0.07
     Ş
    -0.06
    .currentPage
    -0.06
    ্�
    -0.06
     KS
    -0.06
     Bers
    -0.06
     bet
    -0.06
    极
    -0.06
    POSITIVE LOGITS
     世
    0.07
     compliance
    0.07
    _Command
    0.07
    .reloadData
    0.07
    CollectionView
    0.06
    ]=$
    0.06
    \Command
    0.06
     Compliance
    0.06
    ':"
    0.06
     COMMAND
    0.06
    Activations Density 0.003%

    No Known Activations