© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 43354
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash

    The neuron responds to words where the assistant offers help or assistance (e.g. “assist,” “help,” “with”).

    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
    ायत
    -0.07
    yan
    -0.07
     ------------------------------------------------------------
    -0.07
     журн
    -0.06
     letter
    -0.06
     respecting
    -0.06
     trai
    -0.06
     summarizes
    -0.06
     відповідаль
    -0.06
    (area
    -0.06
    POSITIVE LOGITS
     Seq
    0.06
    ์,
    0.06
    ư�
    0.06
     strSQL
    0.06
     vect
    0.06
    ово
    0.06
    Injection
    0.06
    redentials
    0.06
    قد
    0.06
    arter
    0.06
    Activations Density 0.024%

    No Known Activations