© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 40197
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    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
    ::
    -0.08
    domain
    -0.07
    Form
    -0.07
    osten
    -0.07
    chemes
    -0.06
    Specify
    -0.06
    _range
    -0.06
     Ka
    -0.06
     ITEM
    -0.06
     형
    -0.06
    POSITIVE LOGITS
     questioned
    0.06
     attracts
    0.06
    /state
    0.06
     distressed
    0.06
     присутств
    0.06
     protected
    0.05
    peat
    0.05
    (force
    0.05
    فع
    0.05
     информации
    0.05
    Activations Density 0.008%

    No Known Activations