Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 130431
    Prev
    Next
    INDEX
    Explanations

    them

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on the precise decimal values (e.g. “4.75…”) that indicate the percentage of households with children under age 18 in the demographic data.

    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
    462
    -0.07
     getch
    -0.06
    受
    -0.06
    лич
    -0.06
     prá
    -0.06
    ْف
    -0.06
     girlfriends
    -0.06
    AccessType
    -0.06
    ants
    -0.06
    ICollectionView
    -0.06
    POSITIVE LOGITS
    ettel
    0.07
    igel
    0.07
    ToolStripMenuItem
    0.07
     akadem
    0.06
     homeland
    0.06
     сразу
    0.06
    _stuff
    0.06
     visually
    0.06
     compelling
    0.06
     Fraction
    0.06
    Activations Density 0.000%

    No Known Activations