© 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. 27-RESID-POST-AA
    11. 102776
    Prev
    Next
    INDEX
    Explanations

    semicolon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وإ
    -0.07
    .COLUMN
    -0.07
     FOR
    -0.07
    M
    -0.06
    	cache
    -0.06
     //////
    -0.06
     awareness
    -0.06
     мас
    -0.06
    .Large
    -0.06
     puzz
    -0.06
    POSITIVE LOGITS
    .selenium
    0.07
    .app
    0.06
    ioned
    0.06
    ंध
    0.06
     bestellen
    0.06
    Club
    0.06
    'clock
    0.06
    icers
    0.06
    )prepareForSegue
    0.06
    久
    0.06
    Activations Density 0.028%

    No Known Activations