Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 34225
    Prev
    Next
    INDEX
    Explanations

    cul

    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
     Atlas
    -0.08
     tester
    -0.07
     приступ
    -0.06
    anes
    -0.06
     redes
    -0.06
    VertexAttribArray
    -0.06
     forks
    -0.06
     жар
    -0.06
    ColumnsMode
    -0.06
     où
    -0.06
    POSITIVE LOGITS
    担
    0.07
    exp
    0.07
     scripture
    0.07
    ancement
    0.07
     percentile
    0.07
     prot
    0.07
    					      
    0.07
    ~~
    0.06
    erv
    0.06
    Alternative
    0.06
    Activations Density 0.004%

    No Known Activations