© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18627
    Prev
    Next
    INDEX
    Explanations

    every

    np_max-act · gemini-2.0-flash

    The neuron detects quantifying or emphatic tokens that signal an exhaustive, fine-grained focus or intensified attention to specific details.

    oai_token-act-pair · gpt-5-mini
    Triggered by @vetterc0
    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
    Negative Logits
    ec
    -0.07
    _mp
    -0.07
     branch
    -0.07
     Địa
    -0.06
    /kernel
    -0.06
    enchmark
    -0.06
    ckill
    -0.06
    EC
    -0.06
     lat
    -0.06
     buses
    -0.06
    POSITIVE LOGITS
    untu
    0.07
     слово
    0.06
     }
↵
↵
↵
↵
    0.06
     tortured
    0.06
     tabindex
    0.06
    istor
    0.06
     федераль
    0.06
    ↵                        ↵
    0.06
    peace
    0.06
    =forms
    0.06
    Activations Density 0.019%

    No Known Activations