© 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. 118318
    Prev
    Next
    INDEX
    Explanations

    dopamine

    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
    itas
    -0.06
     crab
    -0.06
    ισμός
    -0.06
    есь
    -0.06
     journals
    -0.06
     tử
    -0.06
    qb
    -0.06
    _<
    -0.06
    츠
    -0.05
    Tube
    -0.05
    POSITIVE LOGITS
     dopamine
    0.08
     Pharmac
    0.08
     })),↵
    0.07
     *(*
    0.07
    restaurants
    0.07
    _beta
    0.07
     thẩm
    0.07
     pharmac
    0.07
     Hampton
    0.07
     Decorating
    0.07
    Activations Density 0.003%

    No Known Activations