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. 104397
    Prev
    Next
    INDEX
    Explanations

    two

    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
     Happiness
    -0.07
    (InputStream
    -0.07
    kinson
    -0.07
     Spray
    -0.07
     damage
    -0.06
    .LastName
    -0.06
    Copying
    -0.06
    στά
    -0.06
    _Header
    -0.06
     buying
    -0.06
    POSITIVE LOGITS
     MAGIC
    0.06
     ét
    0.06
     Portuguese
    0.06
     웨
    0.06
    LineStyle
    0.06
    )/
    0.06
     čá
    0.06
    )++;↵
    0.06
     ειδ
    0.06
    ilib
    0.06
    Activations Density 0.039%

    No Known Activations