© 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. 12161
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron does not reliably activate on any tokens and appears to remain inactive across these examples.

    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
     suddenly
    -0.07
     kles
    -0.07
    .manager
    -0.07
    Turn
    -0.07
     name
    -0.07
     retract
    -0.07
     Yet
    -0.06
    .pause
    -0.06
     roses
    -0.06
    Walker
    -0.06
    POSITIVE LOGITS
     الحرب
    0.07
    voje
    0.07
     �
    0.07
    mono
    0.07
    tube
    0.06
    _inches
    0.06
    <dyn
    0.06
    ortho
    0.06
    @d
    0.06
    ของผ
    0.06
    Activations Density 0.039%

    No Known Activations