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. 7-RESID-POST-AA
    6. 25651
    Prev
    Next
    INDEX
    Explanations

    .util

    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
     quo
    -0.08
     работать
    -0.07
     вимог
    -0.07
    _handlers
    -0.07
    _WRAPPER
    -0.06
    覚
    -0.06
    ignet
    -0.06
     chvíli
    -0.06
     들어
    -0.06
     mesa
    -0.06
    POSITIVE LOGITS
    .statusText
    0.07
    OTO
    0.06
    [property
    0.06
    //----------------------------------------------------------------------------
    0.06
     "')
    0.06
    ))/
    0.06
    (length
    0.06
    ("="
    0.06
    /User
    0.06
     :]
    0.06
    Activations Density 0.004%

    No Known Activations