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. 7-RESID-POST-AA
    6. 25272
    Prev
    Next
    INDEX
    Explanations

    .Toast

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _course
    -0.07
    coding
    -0.06
    _KeyDown
    -0.06
    _PK
    -0.06
     واج
    -0.06
     Fallen
    -0.06
    amsung
    -0.06
    Americans
    -0.06
    _parse
    -0.06
    ait
    -0.06
    POSITIVE LOGITS
    LayoutInflater
    0.10
    .Toast
    0.10
    getMockBuilder
    0.08
    createForm
    0.08
    텔
    0.07
    lient
    0.07
    getDoctrine
    0.07
     dự
    0.07
    rf
    0.06
    \FrameworkBundle
    0.06
    Activations Density 0.000%

    No Known Activations