© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 7853
    Prev
    Next
    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash

    This neuron fires on C++ line‐comment markers (“//”), effectively identifying comment lines in the source text.

    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
    company
    -0.07
    ermalink
    -0.07
    monitor
    -0.06
    justify
    -0.06
    fname
    -0.06
    .Init
    -0.06
    agogue
    -0.06
    dataset
    -0.06
    :CGRectMake
    -0.06
    _team
    -0.06
    POSITIVE LOGITS
     airlines
    0.07
                                 ↵
    0.07
    queues
    0.07
     abilities
    0.06
    ड
    0.06
     Nev
    0.06
    솔
    0.06
     mz
    0.06
    //}↵
    0.06
                                  ↵
    0.06
    Activations Density 0.001%

    No Known Activations