© 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. 801
    Prev
    Next
    INDEX
    Explanations

    related

    np_max-act · gemini-2.0-flash

    The neuron chiefly responds to the token “to,” i.e. the infinitive marker/preposition “to.”

    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
    dataSource
    -0.07
    -reply
    -0.07
    δό
    -0.07
     prostate
    -0.07
     Proceedings
    -0.06
    -progress
    -0.06
    项目
    -0.06
     AGAIN
    -0.06
     NETWORK
    -0.06
    .execution
    -0.06
    POSITIVE LOGITS
     vagina
    0.06
    oldt
    0.06
    ContentLoaded
    0.06
     CNBC
    0.06
     clearColor
    0.06
    터
    0.06
    cstdlib
    0.06
     verificar
    0.06
    isol
    0.06
    :@
    0.06
    Activations Density 0.000%

    No Known Activations