© 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. 25901
    Prev
    Next
    INDEX
    Explanations

    ain

    np_max-act · gemini-2.0-flash

    concepts related to grain and its measurement in various forms and contexts.

    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
     entrev
    -0.07
     escort
    -0.07
    _submit
    -0.07
     куда
    -0.07
     스트
    -0.07
     будущ
    -0.07
    .usage
    -0.07
     Chelsea
    -0.06
    coc
    -0.06
     BuzzFeed
    -0.06
    POSITIVE LOGITS
     grain
    0.15
     grains
    0.14
     Grain
    0.12
    IN
    0.09
    ain
    0.08
    in
    0.08
     IN
    0.07
     In
    0.07
    In
    0.07
    -gr
    0.07
    Activations Density 0.003%

    No Known Activations