Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 43977
    Prev
    Next
    INDEX
    Explanations

    immediate values/literals

    np_max-act · gemini-2.0-flash

    The neuron fires on code identifiers for constants (e.g. “IntConstant”, “Constant”) and related import lines, i.e. it spots references to named constant classes in source code.

    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
    sk
    -0.07
    ysics
    -0.06
     DAMAGES
    -0.06
    /preferences
    -0.06
     Distributed
    -0.06
    Ops
    -0.06
     Autonomous
    -0.06
     Tooth
    -0.06
     ผล
    -0.06
     callers
    -0.06
    POSITIVE LOGITS
    my
    0.07
     dùng
    0.06
    addClass
    0.06
     �
    0.06
    '));
    ↵
    0.06
     �
    0.06
     تعد
    0.06
    <|start_header_id|>
    0.06
     Farmer
    0.06
    iba
    0.06
    Activations Density 0.019%

    No Known Activations