© 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. 3-RESID-POST-AA
    11. 95377
    Prev
    Next
    INDEX
    Explanations

    masculine

    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
    -themed
    -0.06
     protesting
    -0.06
    請
    -0.06
    nyder
    -0.06
    .rep
    -0.06
    ี.
    -0.06
    ії
    -0.06
    REAT
    -0.06
    =''):↵
    -0.06
     後
    -0.06
    POSITIVE LOGITS
     masculine
    0.30
     masculinity
    0.18
     feminine
    0.14
     mascul
    0.14
     pristine
    0.09
    ulin
    0.08
     JAXB
    0.08
    cul
    0.07
    秦
    0.07
     insulin
    0.07
    Activations Density 0.002%

    No Known Activations