© 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. 11-RESID-POST-AA
    11. 59110
    Prev
    Next
    INDEX
    Explanations

    half

    np_max-act · gemini-2.0-flash

    This neuron detects descriptions of characters’ mixed heritage or dual-species traits (e.g., “half-human, half-devil kendoka”).

    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
     swapping
    -0.07
     separator
    -0.07
     brawl
    -0.07
    (CharSequence
    -0.07
    presentation
    -0.07
    credential
    -0.06
    >k
    -0.06
    .isEnabled
    -0.06
    iance
    -0.06
     crunchy
    -0.06
    POSITIVE LOGITS
     Cairo
    0.06
     MY
    0.06
     Hop
    0.06
     homeowners
    0.06
     devise
    0.06
     Photo
    0.06
    [token
    0.06
    ｡
    0.06
     stick
    0.06
     DC
    0.06
    Activations Density 0.006%

    No Known Activations