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. 86358
    Prev
    Next
    INDEX
    Explanations

    rash

    np_max-act · gemini-2.0-flash

    This neuron specifically activates on mentions of skin rashes (the word “rash” and its variants).

    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
     joint
    -0.06
     speculation
    -0.06
    oration
    -0.06
     Zeit
    -0.06
     Vers
    -0.06
    ку
    -0.06
     discs
    -0.06
     converters
    -0.06
     divergence
    -0.06
     JS
    -0.06
    POSITIVE LOGITS
     Rash
    0.10
     rash
    0.08
     少
    0.07
     �
    0.07
     administer
    0.07
     persec
    0.07
     retal
    0.07
    .FlatAppearance
    0.07
     Kemal
    0.07
     Qgs
    0.07
    Activations Density 0.002%

    No Known Activations