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. 53931
    Prev
    Next
    INDEX
    Explanations

    plan

    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
     other
    -0.08
    Other
    -0.07
     more
    -0.07
    _other
    -0.07
    TY
    -0.07
     last
    -0.06
    best
    -0.06
    OTHER
    -0.06
     الثاني
    -0.06
    -other
    -0.06
    POSITIVE LOGITS
    .Authorization
    0.07
    RESSION
    0.06
     спри
    0.06
    weather
    0.06
    _CONTACT
    0.06
    anti
    0.06
     Parameters
    0.06
    .deg
    0.06
    ordion
    0.06
    ону
    0.06
    Activations Density 0.205%

    No Known Activations