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. 11-RESID-POST-AA
    6. 34636
    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
     tej
    -0.08
     ids
    -0.08
     btw
    -0.07
     afect
    -0.07
     CONDITIONS
    -0.07
     wnd
    -0.07
    ิถ
    -0.06
     Direction
    -0.06
     mock
    -0.06
    IRECTION
    -0.06
    POSITIVE LOGITS
     informace
    0.07
    <DateTime
    0.07
    輯
    0.06
    #else
    0.06
    _vals
    0.06
    Wal
    0.06
    ymous
    0.06
     GTX
    0.06
     ^{}
    0.06
    ۱۹۶
    0.06
    Activations Density 0.183%

    No Known Activations