© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 125064
    Prev
    Next
    INDEX
    Explanations

    numbered lists

    np_max-act · gemini-2.0-flash

    The neuron identifies numbered list markers (the item‐number tokens at the start of list entries).

    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
     Gener
    -0.07
     Jin
    -0.07
    quote
    -0.06
     establishment
    -0.06
    Et
    -0.06
     Et
    -0.06
    ث
    -0.06
     mCurrent
    -0.06
     divisor
    -0.06
    Out
    -0.06
    POSITIVE LOGITS
    .MON
    0.06
    dj
    0.06
    (IServiceCollection
    0.06
    /moment
    0.06
    -Saharan
    0.06
    的大
    0.06
     Exclude
    0.06
     varios
    0.06
    _serv
    0.06
    (QtGui
    0.06
    Activations Density 0.228%

    No Known Activations