© 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. 30063
    Prev
    Next
    INDEX
    Explanations

    end of message/article

    np_max-act · gemini-2.0-flash

    This neuron specifically detects the sequence of words “to the end of,” as in instructions referring to the end of a message.

    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
    ایر
    -0.06
     کاربرد
    -0.06
    lectric
    -0.06
     мира
    -0.06
     aray
    -0.06
    399
    -0.06
     mevcut
    -0.06
    ีฟ
    -0.06
    ترك
    -0.06
    conda
    -0.06
    POSITIVE LOGITS
    (freq
    0.07
     anunci
    0.07
     recovered
    0.07
    丶
    0.07
     WINAPI
    0.06
    /std
    0.06
    +-+-+-+-+-+-+-+-
    0.06
     end
    0.06
    ({});↵
    0.06
    ---</
    0.06
    Activations Density 0.003%

    No Known Activations