© 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. 91956
    Prev
    Next
    INDEX
    Explanations

    parse

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of backend‐as‐a‐service platforms (e.g. Backand, Parse, Supabase).

    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
    vůli
    -0.08
    datasets
    -0.06
     landscape
    -0.06
    coord
    -0.06
     rigor
    -0.06
    gameObject
    -0.06
    ायन
    -0.06
    _mirror
    -0.06
    정보
    -0.06
     away
    -0.06
    POSITIVE LOGITS
     e
    0.07
     Numeric
    0.07
     Burke
    0.07
     Mining
    0.06
     відбу
    0.06
     खबर
    0.06
    (expect
    0.06
     comprehend
    0.06
    .fromJson
    0.06
     tan
    0.06
    Activations Density 0.012%

    No Known Activations