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. 40476
    Prev
    Next
    INDEX
    Explanations

    cigarette

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “cigarette” (including its close 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
     loans
    -0.06
     수상
    -0.06
     hoof
    -0.06
     therapists
    -0.06
     bas
    -0.06
     holder
    -0.06
     raid
    -0.06
    uk
    -0.06
     Worth
    -0.06
     Noah
    -0.06
    POSITIVE LOGITS
     cigarette
    0.11
     cigarettes
    0.08
     cig
    0.08
    nett
    0.08
    iterate
    0.08
    бом
    0.07
     cigaret
    0.07
    illet
    0.07
     Tells
    0.07
     ジ
    0.07
    Activations Density 0.002%

    No Known Activations