© 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. 58151
    Prev
    Next
    INDEX
    Explanations

    Code and documents

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on references to electrical voltage (i.e., the term “voltage”).

    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
    uter
    -0.06
     было
    -0.06
    ullen
    -0.06
     Zionist
    -0.06
     wit
    -0.06
    }]
    -0.06
     uur
    -0.06
     applicationWill
    -0.06
    ﾞﾞ
    -0.06
     swe
    -0.05
    POSITIVE LOGITS
     cạnh
    0.06
    Miami
    0.06
     Returning
    0.06
    .Void
    0.06
     setDate
    0.06
    uant
    0.06
    شاء
    0.06
     perseverance
    0.06
     delete
    0.06
     newRow
    0.06
    Activations Density 0.000%

    No Known Activations