© 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
    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. 92313
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    IQUE
    -0.07
    RLF
    -0.06
    igor
    -0.06
    ensi
    -0.06
    ión
    -0.06
     pens
    -0.06
    like
    -0.06
    El
    -0.06
    lx
    -0.06
    ({});↵
    -0.06
    POSITIVE LOGITS
    	content
    0.08
    .Next
    0.07
    (test
    0.07
     bandwidth
    0.06
     foreground
    0.06
    ':['
    0.06
    881
    0.06
     edi
    0.06
    addTo
    0.06
    Composer
    0.06
    Activations Density 0.000%

    No Known Activations