© 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. 73625
    Prev
    Next
    INDEX
    Explanations

    learning

    np_max-act · gemini-2.0-flash

    The neuron responds to terms denoting behavioral or cognitive experimental outcomes (e.g. learning, memory, anxiety-like behavior, spatial learning).

    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
     Desktop
    -0.08
    ät
    -0.06
    atinum
    -0.06
    تي
    -0.06
     adip
    -0.06
     smoother
    -0.06
    Thread
    -0.06
    ি
    -0.06
    -tip
    -0.06
    clipse
    -0.06
    POSITIVE LOGITS
     Suffolk
    0.06
    Grant
    0.06
     ﺍ
    0.06
     cityName
    0.06
     UPDATED
    0.06
     dangerously
    0.06
     handicap
    0.06
     insurgency
    0.06
    ्मन
    0.06
     airports
    0.06
    Activations Density 0.007%

    No Known Activations