© 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. 6580
    Prev
    Next
    INDEX
    Explanations

    World

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of the World Wars (e.g. “First World War,” “Second World War”).

    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
    になる
    -0.07
     Protestant
    -0.06
    allest
    -0.06
    如果
    -0.06
    ，如果
    -0.06
    adden
    -0.06
    б
    -0.06
    apes
    -0.06
    fcn
    -0.06
    en
    -0.06
    POSITIVE LOGITS
     hes
    0.07
     vešker
    0.07
    _Version
    0.06
    .archive
    0.06
     Snap
    0.06
     giành
    0.06
     draws
    0.06
     consequ
    0.06
    ็อต
    0.06
    _idxs
    0.06
    Activations Density 0.008%

    No Known Activations