© 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 EvalsExportsinterp-engineNEWAPI 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. 24034
    Prev
    Next
    INDEX
    Explanations

    Charg

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of being charged or accused (morphological forms of "charge" used in legal/criminal contexts).

    oai_token-act-pair · gpt-5-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Sonia
    -0.08
    ious
    -0.08
    ####
    -0.07
    átku
    -0.06
    per
    -0.06
     часов
    -0.06
     in
    -0.06
    -test
    -0.06
    incl
    -0.06
    ق
    -0.06
    POSITIVE LOGITS
    _ITER
    0.08
    =s
    0.08
     QPointF
    0.08
    .logger
    0.07
     WARN
    0.07
     Crush
    0.07
     Mr
    0.07
    ?>
↵
↵
    0.07
    Erot
    0.07
    ko
    0.07
    Activations Density 1.181%

    No Known Activations