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. 19-RESID-POST-AA
    6. 59173
    Prev
    Next
    INDEX
    Explanations

    Harvard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ="+
    -0.08
     dne
    -0.06
     Vũ
    -0.06
    /Sh
    -0.06
     abilities
    -0.06
     ob
    -0.06
     GH
    -0.06
     pob
    -0.06
    .DTO
    -0.06
    _LANG
    -0.06
    POSITIVE LOGITS
     Harvard
    0.07
    147
    0.07
    VN
    0.07
     ATTR
    0.07
     hard
    0.07
    	ms
    0.06
    ivot
    0.06
    -height
    0.06
    feedback
    0.06
     sır
    0.06
    Activations Density 0.003%

    No Known Activations