© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89180
    Prev
    Next
    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash

    This neuron detects academic claims of contribution—phrases where the text says it “provides” (or “provide”) a basis, evidence, framework, or similar support for a finding or model.

    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
    νομα
    -0.07
    .fetch
    -0.07
     mysterious
    -0.07
    ocations
    -0.06
    ону
    -0.06
    ».
    -0.06
    prising
    -0.06
     about
    -0.06
     affordable
    -0.06
     mensagem
    -0.06
    POSITIVE LOGITS
     Ext
    0.07
    aday
    0.06
    -terminal
    0.06
     влас
    0.06
     ober
    0.06
    (audio
    0.06
     jig
    0.06
     RCA
    0.06
     Smash
    0.06
    ラク
    0.06
    Activations Density 0.044%

    No Known Activations