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. 40452
    Prev
    Next
    INDEX
    Explanations

    code; programming

    np_max-act · gemini-2.0-flash

    This neuron activates on code‐looking tokens—especially C# identifiers and method/variable names in Pascal/CamelCase.

    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
     }
    ↵
    ↵
    ↵
    ↵
    -0.07
    +↵
    -0.07
     отношения
    -0.06
    第二
    -0.06
    printf
    -0.06
     Marvel
    -0.06
     بم
    -0.06
    .media
    -0.06
    Acc
    -0.06
     afl
    -0.06
    POSITIVE LOGITS
     artwork
    0.08
    archs
    0.06
    close
    0.06
    ламент
    0.06
     extents
    0.06
    .recipe
    0.06
     Sabb
    0.06
    ательных
    0.05
    (tokens
    0.05
    ъем
    0.05
    Activations Density 0.442%

    No Known Activations