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. 130407
    Prev
    Next
    INDEX
    Explanations

    Experiences and details

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens containing decimal points (floating-point numbers).

    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
    という
    -0.07
     commissioned
    -0.07
    XXXX
    -0.06
    (enable
    -0.06
     fus
    -0.06
    續
    -0.06
    unei
    -0.06
    (indent
    -0.06
     jsonString
    -0.06
    Require
    -0.06
    POSITIVE LOGITS
    came
    0.08
     veterans
    0.07
     overs
    0.06
    周
    0.06
     fill
    0.06
    صب
    0.06
     unsub
    0.06
     advantages
    0.06
     бли
    0.06
    members
    0.06
    Activations Density 0.001%

    No Known Activations