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. 84521
    Prev
    Next
    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash

    This neuron fires on XML-style documentation comments and their markup (e.g. the “///” comment markers and tags like `<summary>`/`<remarks>`).

    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
     Hier
    -0.07
    比較
    -0.07
     constellation
    -0.07
     quotient
    -0.06
    294
    -0.06
     Achievement
    -0.06
    iar
    -0.06
    enu
    -0.06
     constructed
    -0.06
    Hier
    -0.06
    POSITIVE LOGITS
     правила
    0.07
     vlast
    0.07
     перепис
    0.06
    ')))
    0.06
    _ack
    0.06
    +-+-
    0.06
     rửa
    0.06
     постро
    0.06
    .matches
    0.06
    #SBATCH
    0.06
    Activations Density 0.011%

    No Known Activations