© 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. 19-RESID-POST-AA
    11. 127116
    Prev
    Next
    INDEX
    Explanations

    company names

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rale
    -0.08
     cliff
    -0.07
    hal
    -0.07
    bundle
    -0.07
    lying
    -0.07
    _bonus
    -0.07
    备注
    -0.07
    illin
    -0.06
    _String
    -0.06
    ánh
    -0.06
    POSITIVE LOGITS
    _CONTINUE
    0.06
     같은
    0.06
     Tas
    0.06
     ніколи
    0.06
    HP
    0.05
     státu
    0.05
     hated
    0.05
     يمكن
    0.05
    이었다
    0.05
    äge
    0.05
    Activations Density 0.039%

    No Known Activations