© 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
    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. 5698
    Prev
    Next
    INDEX
    Explanations

    cat

    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
    imbledon
    -0.07
    овер
    -0.07
     качестве
    -0.07
     defiant
    -0.06
    drž
    -0.06
    ugas
    -0.06
     маст
    -0.06
     ух
    -0.06
     подраз
    -0.06
     doporuč
    -0.06
    POSITIVE LOGITS
    ak
    0.08
     caring
    0.07
    驗
    0.07
    AK
    0.06
     conditional
    0.06
     bonding
    0.06
    Visual
    0.06
    enk
    0.06
    confirm
    0.06
     retina
    0.06
    Activations Density 0.000%

    No Known Activations