© 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. 89063
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash

    The neuron responds to the special header and separator tokens that mark the boundaries of the assistant’s response (e.g. the “assistant” header and its start/end markers).

    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
     sign
    -0.08
    두
    -0.08
     suspicions
    -0.07
    軍
    -0.06
    blend
    -0.06
     signs
    -0.06
    Bond
    -0.06
     Bord
    -0.06
    uve
    -0.06
    受
    -0.06
    POSITIVE LOGITS
    (encoder
    0.06
    :NS
    0.06
    ندگی
    0.06
     mandated
    0.06
     Nb
    0.06
    legates
    0.06
    جل
    0.06
     Welch
    0.06
    �
    0.06
     Alpine
    0.06
    Activations Density 0.122%

    No Known Activations