© 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. 23-RESID-POST-AA
    11. 105109
    Prev
    Next
    INDEX
    Explanations

    Sentence fragments

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omedical
    -0.07
    _RATIO
    -0.07
     '".
    -0.07
    事情
    -0.07
     realpath
    -0.06
     ASP
    -0.06
    -density
    -0.06
    _PCIE
    -0.06
     Dương
    -0.06
     Iter
    -0.06
    POSITIVE LOGITS
    float
    0.06
     merge
    0.06
     мас
    0.06
    ];
↵
    0.06
    シア
    0.06
     enrich
    0.06
    …)↵↵
    0.06
     。↵
    0.06
    Mixed
    0.06
     Rück
    0.06
    Activations Density 0.109%

    No Known Activations