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. 74614
    Prev
    Next
    INDEX
    Explanations

    Programming code/documentation

    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
     gab
    -0.06
    iations
    -0.06
     Penny
    -0.06
    <?=
    -0.06
     snacks
    -0.06
     Mits
    -0.06
    .credentials
    -0.06
    sql
    -0.06
    }},↵
    -0.06
     laz
    -0.06
    POSITIVE LOGITS
     Associates
    0.07
     Vincent
    0.06
    _INTERNAL
    0.06
    Joint
    0.06
     exposures
    0.06
    技術
    0.06
    (defvar
    0.06
    ेन
    0.06
     catches
    0.06
     affidavit
    0.06
    Activations Density 0.064%

    No Known Activations