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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 85519
    Prev
    Next
    INDEX
    Explanations

    combe

    np_max-act · gemini-2.0-flash

    Tokens that mark document structure or metadata—section/table/figure headings, labels and nearby numeric/table entries.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    4
    -0.07
    5
    -0.07
    عان
    -0.07
    andro
    -0.07
     Mayo
    -0.07
     mír
    -0.07
     выше
    -0.07
     nabíd
    -0.06
    anos
    -0.06
    ѕ
    -0.06
    POSITIVE LOGITS
    _alg
    0.07
    Toolkit
    0.07
    NSS
    0.06
    rowned
    0.06
     dictionaries
    0.06
     Da
    0.06
     mitochond
    0.06
     �
    0.06
    *log
    0.06
     bytecode
    0.06
    Activations Density 18.694%

    No Known Activations