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. 86256
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric or decimal measurement tokens (e.g. percentages, sequence identity scores, phylogenetic distances, and other scientific numerical values).

    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
     erro
    -0.07
     تور
    -0.07
    工業
    -0.07
    Unmarshaller
    -0.07
     horm
    -0.06
     во
    -0.06
     Jacqu
    -0.06
    誠
    -0.06
    십시오
    -0.06
     Eng
    -0.06
    POSITIVE LOGITS
    &type
    0.08
    _ZONE
    0.07
    -changing
    0.06
    imizeBox
    0.06
     cook
    0.06
    (BASE
    0.06
    =output
    0.06
     ATF
    0.06
    _series
    0.06
    pure
    0.06
    Activations Density 0.018%

    No Known Activations