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. 85987
    Prev
    Next
    INDEX
    Explanations

    Maximums and peaks

    np_max-act · gemini-2.0-flash

    This neuron detects words signaling numerical extremes—like “peak,” “maximum,” or “nadir”—that mark high or low points in data.

    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
     karakter
    -0.07
    الك
    -0.07
     conhec
    -0.06
    pcl
    -0.06
     Ment
    -0.06
     Hond
    -0.06
    forder
    -0.06
    107
    -0.06
     preca
    -0.06
     lasting
    -0.06
    POSITIVE LOGITS
    PermissionsResult
    0.07
     gái
    0.07
     Camden
    0.07
     languages
    0.06
     drums
    0.06
     Northwest
    0.06
    =array
    0.06
     horror
    0.06
    :::::::
    0.06
    _EXP
    0.06
    Activations Density 0.046%

    No Known Activations