© 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. 57624
    Prev
    Next
    INDEX
    Explanations

    trilogy

    np_max-act · gemini-2.0-flash

    references to specific literary works or adaptations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on mentions of “rings” (as in The Lord of the Rings) or “trilogy/-logía” across different languages.

    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
     Nurses
    -0.07
    атом
    -0.07
     외
    -0.06
    \/\/
    -0.06
     Waters
    -0.06
     "<
    -0.06
     recyclerView
    -0.06
    ////////////////////////////////////////////////
    -0.06
     nightmares
    -0.06
    ('*',
    -0.06
    POSITIVE LOGITS
    σου
    0.06
     trough
    0.06
    _CANCEL
    0.06
     :↵
    0.06
    Crud
    0.06
    ังน
    0.06
    τια
    0.06
     tweak
    0.06
    Scale
    0.06
    SPARENT
    0.06
    Activations Density 0.010%

    No Known Activations