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. 15-RESID-POST-AA
    6. 59635
    Prev
    Next
    INDEX
    Explanations

    errors and troubleshooting

    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
     particle
    -0.07
    ("{}
    -0.07
    .SERVER
    -0.07
     gotta
    -0.07
     Republican
    -0.07
    .subplot
    -0.06
    ул
    -0.06
    .LastName
    -0.06
    GroupId
    -0.06
    -consuming
    -0.06
    POSITIVE LOGITS
    Nested
    0.07
    (queue
    0.06
    _armor
    0.06
     DON
    0.06
     BAT
    0.06
    Improved
    0.06
     Throne
    0.06
    ètres
    0.06
    Magn
    0.06
     spring
    0.06
    Activations Density 0.022%

    No Known Activations