© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92424
    Prev
    Next
    INDEX
    Explanations

    Neutral

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the word “neutral” (often capitalized as “Neutral”) in section headings or titles.

    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
    arendra
    -0.07
     اج
    -0.06
     Sudoku
    -0.06
    cosystem
    -0.06
     Hag
    -0.06
     Vive
    -0.06
     Worce
    -0.06
    ologi
    -0.06
     rise
    -0.06
    agnitude
    -0.06
    POSITIVE LOGITS
     neutral
    0.13
     Neutral
    0.11
    Neutral
    0.10
     indifference
    0.09
    neutral
    0.09
    _nbr
    0.08
     venues
    0.08
     counter
    0.07
    ر
    0.07
    ystone
    0.07
    Activations Density 0.006%

    No Known Activations