© 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. 59042
    Prev
    Next
    INDEX
    Explanations

    Heat dissipation/escape

    np_max-act · gemini-2.0-flash

    The neuron fires on terms discussing the passage or discharge of air and moisture (e.g. “discharged,” “air permeability,” “sweat”).

    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
     Justin
    -0.07
     Eff
    -0.06
    aln
    -0.06
    Justin
    -0.06
    ken
    -0.06
     "@"
    -0.06
    ">
↵
    -0.06
    рут
    -0.06
    ('.');↵
    -0.06
    '));↵↵
    -0.06
    POSITIVE LOGITS
     hafif
    0.07
     anne
    0.06
     FORMAT
    0.06
    prepare
    0.06
    ValueType
    0.06
    inform
    0.06
    starts
    0.06
    <'
    0.06
    _GOOD
    0.06
    (simp
    0.06
    Activations Density 0.014%

    No Known Activations