© 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 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. 38224
    Prev
    Next
    INDEX
    Explanations

    Opinions, beliefs or problems

    np_max-act · gemini-2.0-flash

    The neuron detects the “If you believe this is an error…” feedback‐solicitation phrase, especially words like “believe,” “this,” “is,” and “error.”

    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
    	unit
    -0.06
     Aster
    -0.06
     stats
    -0.06
     soundtrack
    -0.06
     timestamp
    -0.06
    (artist
    -0.06
    -server
    -0.06
    .chunk
    -0.06
    .info
    -0.06
     :-
    -0.06
    POSITIVE LOGITS
    знача
    0.07
    ，全
    0.07
    そんな
    0.06
    edics
    0.06
     ;;↵
    0.06
    ihan
    0.06
    _bd
    0.06
    ัญ
    0.06
    .describe
    0.06
    	puts
    0.06
    Activations Density 0.010%

    No Known Activations