© 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. 128554
    Prev
    Next
    INDEX
    Explanations

    f

    np_max-act · gemini-2.0-flash

    This neuron spotlights hexadecimal tokens (memory addresses and offsets) in crash backtraces.

    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
     schöne
    -0.07
     Older
    -0.06
    _goal
    -0.06
    \xb
    -0.06
    _TERM
    -0.06
     sche
    -0.06
    (_("
    -0.06
    (numpy
    -0.06
    rides
    -0.06
     Negro
    -0.06
    POSITIVE LOGITS
    _gradients
    0.07
    説明
    0.06
     stupidity
    0.06
    �
    0.06
     ठ
    0.06
    737
    0.06
    請
    0.06
    _specific
    0.06
    IGATION
    0.06
    _previous
    0.06
    Activations Density 0.002%

    No Known Activations