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. 128133
    Prev
    Next
    INDEX
    Explanations

    Shadow

    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
     crate
    -0.07
     hoá
    -0.07
     ділян
    -0.07
     python
    -0.06
     org
    -0.06
    nist
    -0.06
    chemical
    -0.06
    ecial
    -0.06
     Clare
    -0.06
    \helpers
    -0.06
    POSITIVE LOGITS
     Shadow
    0.13
     shadow
    0.12
    shadow
    0.11
    Shadow
    0.11
     shadows
    0.08
     spotlight
    0.08
     Shadows
    0.08
     Thunder
    0.07
     chambers
    0.07
     Ά
    0.07
    Activations Density 0.008%

    No Known Activations