Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 121847
    Prev
    Next
    INDEX
    Explanations

    fine

    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
    coef
    -0.07
    HAV
    -0.07
     in
    -0.07
     suicide
    -0.07
    ilerinin
    -0.07
    -circle
    -0.07
     Shooting
    -0.06
     FOR
    -0.06
     Suicide
    -0.06
    كون
    -0.06
    POSITIVE LOGITS
    .scss
    0.07
     ký
    0.06
    (jj
    0.06
    sim
    0.06
    "][$
    0.06
    .Compare
    0.06
     Australians
    0.06
     Vert
    0.06
    成本
    0.05
    -founder
    0.05
    Activations Density 0.014%

    No Known Activations