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. 11-RESID-POST-AA
    6. 26056
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ことを
    -0.08
    _PROPERTY
    -0.06
    utdown
    -0.06
    FindBy
    -0.06
    ICTURE
    -0.06
    .CurrentCulture
    -0.06
    unque
    -0.06
     ticaret
    -0.06
    _PATH
    -0.06
    180
    -0.06
    POSITIVE LOGITS
     of
    0.13
     Of
    0.12
     OF
    0.11
    -of
    0.10
    of
    0.10
    Of
    0.09
    _of
    0.09
    .of
    0.08
    _OF
    0.08
    из
    0.08
    Activations Density 0.252%

    No Known Activations