© 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
    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. 85691
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash

    the names of bacterial species (i.e. microbial strains tested in antimicrobial activity assays)

    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
    INDER
    -0.07
    (counter
    -0.06
     survival
    -0.06
     skies
    -0.06
     Jeffrey
    -0.06
    ("----------------
    -0.06
     Christie
    -0.06
    (Time
    -0.06
     Harrison
    -0.06
    .Runtime
    -0.06
    POSITIVE LOGITS
    Gold
    0.06
     nfl
    0.06
     inexperienced
    0.06
    “(
    0.06
     fulfill
    0.06
    上が
    0.06
    _popup
    0.06
    rt
    0.06
    atırım
    0.06
    .DEFINE
    0.06
    Activations Density 0.009%

    No Known Activations