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

    Neuronpedia

    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. 11-RESID-POST-AA
    11. 9274
    Prev
    Next
    INDEX
    Explanations

    damage

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of physical damage to products or goods (e.g., “damaged,” “broken,” “goods delivered damaged”).

    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
    errno
    -0.06
    高速
    -0.06
     backgrounds
    -0.06
     léč
    -0.06
    評
    -0.06
     Pool
    -0.06
    keepers
    -0.06
     theta
    -0.06
    Lock
    -0.06
     galaxies
    -0.06
    POSITIVE LOGITS
     Protected
    0.07
    OutOfRangeException
    0.07
     ofere
    0.07
    _EXTERN
    0.07
    軟
    0.07
    uala
    0.06
    ái
    0.06
     spared
    0.06
    複
    0.06
     tô
    0.06
    Activations Density 0.009%

    No Known Activations