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. 11-RESID-POST-AA
    6. 75907
    Prev
    Next
    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash

    technical explanations related to programming, particularly in the context of C and graphical rendering techniques.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .protocol
    -0.08
    igrams
    -0.07
    :UIButtonType
    -0.07
    .Println
    -0.07
    .metro
    -0.07
     분류
    -0.07
    itus
    -0.07
    .locations
    -0.06
     �
    -0.06
    .WaitFor
    -0.06
    POSITIVE LOGITS
    (\"
    0.07
     ;
    0.07
    uper
    0.07
    ですね
    0.06
     nuevas
    0.06
    Ya
    0.06
    PER
    0.06
    =\"
    0.06
    _VAL
    0.06
     van
    0.06
    Activations Density 0.058%

    No Known Activations