© 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. 27-RESID-POST-AA
    11. 104000
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    好像
    -0.07
    fi
    -0.06
    )-
    -0.06
     betting
    -0.06
    Quit
    -0.06
     kan
    -0.06
    =="
    -0.06
    )--
    -0.06
     사무
    -0.06
    _vid
    -0.06
    POSITIVE LOGITS
    แสง
    0.06
    우리
    0.06
     hour
    0.06
     مقاو
    0.06
     dormant
    0.06
    reland
    0.06
    态
    0.06
    �
    0.06
    。当
    0.06
    .parseColor
    0.06
    Activations Density 0.052%

    No Known Activations