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. 8409
    Prev
    Next
    INDEX
    Explanations

    greetings and wishes

    np_max-act · gemini-2.0-flash

    The neuron is looking for the special header‐ID markers (like <|start_header_id|> and <|end_header_id|>) and their numeric IDs in the text.

    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
    гал
    -0.07
    농
    -0.06
     多
    -0.06
     konut
    -0.06
     Contracts
    -0.06
    SpinBox
    -0.06
    amak
    -0.06
    .Task
    -0.06
     Ted
    -0.06
     CGFloat
    -0.06
    POSITIVE LOGITS
    icho
    0.08
    (phase
    0.07
     місті
    0.07
    inscription
    0.07
     videa
    0.07
    .cache
    0.06
    (resp
    0.06
    sg
    0.06
     Zion
    0.06
    undra
    0.06
    Activations Density 0.051%

    No Known Activations