© 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. 3-RESID-POST-AA
    6. 123081
    Prev
    Next
    INDEX
    Explanations

    stake

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ')+
    -0.07
    DET
    -0.07
     "]"
    -0.07
    |
    -0.07
     '''
    ↵
    -0.07
     see
    -0.06
    >
    -0.06
    >An
    -0.06
     del
    -0.06
     enum
    -0.06
    POSITIVE LOGITS
     Stake
    0.17
     stake
    0.13
    aking
    0.10
     stakes
    0.09
    akes
    0.08
    ake
    0.08
    staking
    0.08
     ovarian
    0.06
    UserRole
    0.06
    zbek
    0.06
    Activations Density 0.004%

    No Known Activations