Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RESID-POST-AA
    6. 123136
    Prev
    Next
    INDEX
    Explanations

    work

    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_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
    >List
    -0.08
    .neg
    -0.06
    longitude
    -0.06
    _WIDTH
    -0.06
     Cad
    -0.06
     practitioners
    -0.06
     compiled
    -0.06
    )s
    -0.06
     Jury
    -0.06
     dramas
    -0.06
    POSITIVE LOGITS
    activo
    0.07
    d
    0.07
    oin
    0.07
    iek
    0.07
    (cond
    0.07
    (Temp
    0.06
     выс
    0.06
    〈
    0.06
    农业
    0.06
     المن
    0.06
    Activations Density 0.026%

    No Known Activations