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. 126736
    Prev
    Next
    INDEX
    Explanations

    Part

    np_max-act · gemini-2.0-flash

    This neuron activates on section or part headings, especially occurrences of the word “Part” (often followed by a number or subtitle).

    oai_token-act-pair · o4-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
    enez
    -0.07
     zvý
    -0.07
     Lucifer
    -0.07
    oxy
    -0.06
     Hoe
    -0.06
     Wu
    -0.06
     Schneider
    -0.06
     Cohen
    -0.06
     McKenzie
    -0.06
    Watcher
    -0.06
    POSITIVE LOGITS
     part
    0.16
     Part
    0.14
     parts
    0.13
    Part
    0.12
     PART
    0.11
     Parts
    0.11
    part
    0.11
    _Part
    0.10
    art
    0.10
    PART
    0.09
    Activations Density 0.077%

    No Known Activations