© 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. 110256
    Prev
    Next
    INDEX
    Explanations

    special cases

    np_max-act · gemini-2.0-flash

    concepts related to mathematical optimization and generalizations in theoretical contexts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects mentions of a concept being generalized or described as including particular cases (e.g. “generalization,” “includes … as special cases”).

    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
     mes
    -0.07
     features
    -0.07
     nil
    -0.06
    .GetDirectoryName
    -0.06
     соци
    -0.06
     defeat
    -0.06
     manual
    -0.06
    _path
    -0.06
     chron
    -0.06
    лер
    -0.06
    POSITIVE LOGITS
    _PROTO
    0.07
    (aa
    0.06
     app
    0.06
     बय
    0.06
     RandomForest
    0.06
     тяжел
    0.06
    .onViewCreated
    0.06
     εμφ
    0.06
     acompañ
    0.06
    _APP
    0.06
    Activations Density 0.038%

    No Known Activations