© 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. 11-RESID-POST-AA
    11. 57726
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron does not activate on any of the text—it does not reliably detect any particular pattern.

    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
    Worksheet
    -0.07
     tempt
    -0.06
    <W
    -0.06
    ências
    -0.06
    (system
    -0.06
    OMIC
    -0.06
     yaklaşık
    -0.06
     قرارداد
    -0.06
    rschein
    -0.06
    osopher
    -0.06
    POSITIVE LOGITS
     grand
    0.06
    Safety
    0.06
    点击
    0.06
     Melee
    0.06
     offset
    0.06
    $error
    0.06
    技
    0.06
    \model
    0.06
    LayoutConstraint
    0.05
    �
    0.05
    Activations Density 0.019%

    No Known Activations