© 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. 66103
    Prev
    Next
    INDEX
    Explanations

    question marks

    np_max-act · gemini-2.0-flash

    questions asking about the model's capabilities (words/phrases like "what are you capable of doing" and similar capability inquiries).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    129
    -0.07
    endregion
    -0.07
     billboard
    -0.06
    258
    -0.06
    _OF
    -0.06
     мистецт
    -0.06
     tease
    -0.06
     CAMERA
    -0.06
    everything
    -0.06
    vac
    -0.06
    POSITIVE LOGITS
    .Alert
    0.07
    .stroke
    0.07
     Membership
    0.06
     Electronics
    0.06
    -close
    0.06
     gradually
    0.06
     Compar
    0.06
    physical
    0.06
     physical
    0.06
    (iterator
    0.06
    Activations Density 0.067%

    No Known Activations