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. 15-RESID-POST-AA
    6. 21197
    Prev
    Next
    INDEX
    Explanations

    center

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SHIFT
    -0.08
    ysics
    -0.06
    )animated
    -0.06
    EPROM
    -0.06
     pochop
    -0.06
    tec
    -0.06
    .WindowManager
    -0.06
     Respir
    -0.06
    (paths
    -0.06
     Astronomy
    -0.06
    POSITIVE LOGITS
    Ѕ
    0.08
    Six
    0.07
    jectory
    0.06
    �
    0.06
     kde
    0.06
    Brightness
    0.06
    ิย
    0.06
    quarters
    0.06
    formatted
    0.06
     startDate
    0.06
    Activations Density 0.000%

    No Known Activations