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. 23-RESID-POST-AA
    6. 40589
    Prev
    Next
    INDEX
    Explanations

    product codes and details

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilin
    -0.07
     irrig
    -0.07
     enriched
    -0.06
    %m
    -0.06
     Sequence
    -0.06
     pand
    -0.06
     있으며
    -0.06
     renders
    -0.06
     Possible
    -0.06
     aborted
    -0.06
    POSITIVE LOGITS
     hlavně
    0.07
     CGSizeMake
    0.07
     goals
    0.06
     Sach
    0.06
     qry
    0.06
     قطر
    0.06
    verige
    0.06
    ...");
    ↵
    0.06
    specifier
    0.06
    _stmt
    0.06
    Activations Density 0.045%

    No Known Activations