© 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. 91920
    Prev
    Next
    INDEX
    Explanations

    Operation or management of locations

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of who operates or manages a facility (e.g. phrases like “is operated by” or “managed by”).

    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
    UsageId
    -0.07
    TabPage
    -0.06
    \
↵
    -0.06
    imate
    -0.06
    .tabs
    -0.06
    たし
    -0.06
     Olsen
    -0.06
    ับส
    -0.06
    ühl
    -0.06
    IntoConstraints
    -0.06
    POSITIVE LOGITS
    stop
    0.07
     maintains
    0.06
     descriptors
    0.06
     trat
    0.06
    eq
    0.06
     LINK
    0.06
     qualification
    0.06
     flown
    0.06
    Limit
    0.06
     accom
    0.06
    Activations Density 0.013%

    No Known Activations