© 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. 110807
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on the “consideration” concept—i.e. tokens involving “consider” (like “consideration,” “considering”).

    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
     cleanup
    -0.07
     gamers
    -0.07
     identification
    -0.07
     duties
    -0.06
     responsibilities
    -0.06
     Surveillance
    -0.06
    Most
    -0.06
     حی
    -0.06
     shove
    -0.06
     explores
    -0.06
    POSITIVE LOGITS
    TJ
    0.08
    ?!↵↵
    0.07
    NS
    0.07
    .”↵↵↵↵
    0.07
     (
    0.06
     |↵↵
    0.06
      ↵↵↵
    0.06
     +/-
    0.06
                           ↵
    0.06
    .cart
    0.06
    Activations Density 0.003%

    No Known Activations