© 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. 111675
    Prev
    Next
    INDEX
    Explanations

    of

    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
    очного
    -0.07
     ngOnInit
    -0.07
     numerous
    -0.06
    プロ
    -0.06
     además
    -0.06
     عزیز
    -0.06
     TABLE
    -0.06
     jc
    -0.06
     oxidation
    -0.06
    .long
    -0.06
    POSITIVE LOGITS
    Proxy
    0.07
     liber
    0.07
    CEO
    0.07
    фі
    0.06
     FIRE
    0.06
     날
    0.06
    oultry
    0.06
    uh
    0.06
    etections
    0.06
    뉴스
    0.06
    Activations Density 0.000%

    No Known Activations