© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 4739
    Prev
    Next
    INDEX
    Explanations

    .

    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
     Specialty
    -0.07
     Rock
    -0.06
     peach
    -0.06
     Neighbor
    -0.06
     accompanies
    -0.06
    male
    -0.06
    erken
    -0.06
    acente
    -0.06
    icked
    -0.06
     Natal
    -0.06
    POSITIVE LOGITS
    unlikely
    0.07
    CAA
    0.07
    yu
    0.07
     lowering
    0.07
    .INT
    0.06
    omination
    0.06
    chw
    0.06
     indexer
    0.06
     simulator
    0.06
     För
    0.06
    Activations Density 0.045%

    No Known Activations