© 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. 30482
    Prev
    Next
    INDEX
    Explanations

    optimal

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of finding or defining the “optimal” parameter or setting in the text.

    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
     Quiet
    -0.06
    _evaluation
    -0.06
    ione
    -0.06
    ocrin
    -0.06
     photographs
    -0.06
     馬
    -0.06
    ’all
    -0.06
    .TEST
    -0.06
     trainer
    -0.06
    _multi
    -0.06
    POSITIVE LOGITS
     Sử
    0.07
     Indicates
    0.07
     Hopefully
    0.07
     menggunakan
    0.06
     CURL
    0.06
    ellschaft
    0.06
     poss
    0.06
     harga
    0.06
    VertexAttrib
    0.06
    persons
    0.06
    Activations Density 0.034%

    No Known Activations