© 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. 38764
    Prev
    Next
    INDEX
    Explanations

    optimization problems

    np_max-act · gemini-2.0-flash

    The neuron fires on technical “action” and method‐describing terms (solve, optimization, formulation, algorithm, problem, convex, etc.) that outline the research’s methodological contributions.

    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
     Hell
    -0.07
    Hell
    -0.07
     květ
    -0.07
    Remark
    -0.07
    +s
    -0.07
    出
    -0.06
     deem
    -0.06
    _threads
    -0.06
    Mess
    -0.06
    _SKIP
    -0.06
    POSITIVE LOGITS
    ımızda
    0.08
    ereco
    0.07
    าญ
    0.07
     Затем
    0.07
    brain
    0.07
    .rd
    0.06
     BEEN
    0.06
    CR
    0.06
    perienced
    0.06
     paperwork
    0.06
    Activations Density 0.010%

    No Known Activations