Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 40398
    Prev
    Next
    INDEX
    Explanations

    URLs and code

    np_max-act · gemini-2.0-flash

    This neuron activates on the individual name segments of package and import paths (e.g. the top‐level domain or organization identifiers in Java import/package statements).

    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
    .jpg
    -0.06
    .JPG
    -0.06
    097
    -0.06
    lament
    -0.06
    ольш
    -0.06
    .tif
    -0.06
     Manufacturers
    -0.06
     '@
    -0.06
    γον
    -0.06
    com
    -0.06
    POSITIVE LOGITS
     Retry
    0.07
    Acceler
    0.07
    .OPEN
    0.07
     compassionate
    0.06
    َج
    0.06
    Go
    0.06
    LEVEL
    0.06
    ّ
    0.06
     datap
    0.06
     जनवर
    0.06
    Activations Density 0.006%

    No Known Activations