Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 7459
    Prev
    Next
    INDEX
    Explanations

    ל

    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
     таб
    -0.06
    .png
    -0.06
     ภ
    -0.06
    cen
    -0.06
     nunca
    -0.06
    (Photo
    -0.06
     Jake
    -0.06
    -тех
    -0.06
     невозможно
    -0.06
    Think
    -0.06
    POSITIVE LOGITS
    ]);
    ↵
    0.07
    .array
    0.06
    pcodes
    0.06
    .clf
    0.06
    (to
    0.06
    _cores
    0.06
    leetcode
    0.06
    shortcode
    0.06
    出し
    0.06
    otypes
    0.06
    Activations Density 0.004%

    No Known Activations