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. 5546
    Prev
    Next
    INDEX
    Explanations

    explanations

    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
    _opts
    -0.06
     películ
    -0.06
    Kick
    -0.06
    一度
    -0.06
    ávací
    -0.06
     head
    -0.06
     наличии
    -0.06
     tổng
    -0.06
    уры
    -0.06
     работе
    -0.06
    POSITIVE LOGITS
    _FREQ
    0.08
     Tate
    0.07
     scri
    0.07
    VertexAttrib
    0.07
    setError
    0.06
    (per
    0.06
    TEMPL
    0.06
    .fml
    0.06
    _IList
    0.06
     matches
    0.06
    Activations Density 0.017%

    No Known Activations