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. 84428
    Prev
    Next
    INDEX
    Explanations

    oc

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the character sequence “oc” within tokens.

    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
    黑
    -0.06
     přist
    -0.06
     plá
    -0.06
     ai
    -0.06
    �
    -0.06
     coatings
    -0.06
    =wx
    -0.06
     sayılı
    -0.06
     rab
    -0.06
    ारन
    -0.06
    POSITIVE LOGITS
    署
    0.06
    _article
    0.06
    -rest
    0.06
    reports
    0.06
     Experience
    0.06
    SSIP
    0.06
    enta
    0.06
    dimension
    0.06
    .spec
    0.06
     '{$
    0.06
    Activations Density 0.000%

    No Known Activations