© 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. 89142
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    The neuron is primarily firing on named‐entity tokens—capitalized words like person/place names (e.g. “Wayne,” “Elmhurst”) and temporal/date terms (e.g. “First,” “October,” “November”).

    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
     σχ
    -0.06
    (core
    -0.06
     ~>
    -0.06
     Peaks
    -0.06
    ónica
    -0.06
    teří
    -0.06
     Fellowship
    -0.06
    .putText
    -0.06
    [:
    -0.06
    Flo
    -0.06
    POSITIVE LOGITS
    IGHT
    0.08
     офі
    0.07
     reim
    0.07
     좀
    0.07
     zipper
    0.06
    find
    0.06
    点击
    0.06
    178
    0.06
    _receipt
    0.06
    ες
    0.06
    Activations Density 0.044%

    No Known Activations