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. 130354
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash

    This neuron primarily fires on tokens representing decimal‐style numerical values (e.g. “0.257080078125,” “1.9736328125,” etc.).

    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
     afternoon
    -0.06
     swift
    -0.06
     PLAY
    -0.06
    ifacts
    -0.06
     yaparak
    -0.06
    、この
    -0.06
     существует
    -0.06
    在线观看
    -0.06
    руд
    -0.06
    lucent
    -0.06
    POSITIVE LOGITS
    ($("#
    0.07
    택
    0.06
     getPath
    0.06
    IDES
    0.06
    게
    0.06
     Scores
    0.06
     Illustr
    0.06
     WITH
    0.06
    娘
    0.06
     twee
    0.06
    Activations Density 0.027%

    No Known Activations