© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125089
    Prev
    Next
    INDEX
    Explanations

    legal disputes

    np_max-act · gemini-2.0-flash

    The neuron identifies auxiliary “was” forms that introduce passive‐voice constructions.

    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
    Assistant
    -0.08
    <decimal
    -0.07
    ु
    -0.06
     DG
    -0.06
     desta
    -0.06
     NDP
    -0.06
    ILI
    -0.06
     Nice
    -0.06
     несп
    -0.06
    .ContentAlignment
    -0.06
    POSITIVE LOGITS
    .GetType
    0.07
    (hero
    0.07
     vont
    0.07
    (attribute
    0.06
     голос
    0.06
    (dy
    0.06
     Card
    0.06
    (col
    0.06
    $(
    0.06
     fairly
    0.06
    Activations Density 0.037%

    No Known Activations