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. 15-RESID-POST-AA
    6. 84219
    Prev
    Next
    INDEX
    Explanations

    more

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =F
    -0.08
    �
    -0.06
    elik
    -0.06
     якщо
    -0.06
    GLE
    -0.06
     rád
    -0.06
    jadi
    -0.06
     mj
    -0.06
     doesnt
    -0.06
    osomes
    -0.06
    POSITIVE LOGITS
    posted
    0.07
    browse
    0.07
    ataloader
    0.06
    (find
    0.06
    57
    0.06
    translated
    0.06
    ificação
    0.06
    29
    0.06
     fundraiser
    0.06
    MYSQL
    0.06
    Activations Density 0.001%

    No Known Activations