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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 1022
    Prev
    Next
    INDEX
    Explanations

    file paths and code

    np_max-act · gemini-2.0-flash

    code snippets and references to coding functions and libraries.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron identifies the special “end of header” token marking the close of a message header.

    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
     هفت
    -0.07
    허
    -0.07
     должна
    -0.06
    _SEARCH
    -0.06
    lift
    -0.06
     athletics
    -0.06
    ิท
    -0.06
     glory
    -0.06
    xEC
    -0.06
    KHR
    -0.06
    POSITIVE LOGITS
     (;
    0.07
    _vertex
    0.07
    �
    0.06
     Про
    0.06
    ists
    0.06
    .Println
    0.06
    ols
    0.06
     munch
    0.06
     Replay
    0.06
     Came
    0.06
    Activations Density 0.015%

    No Known Activations