© 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. 58015
    Prev
    Next
    INDEX
    Explanations

    scientific analysis

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of molecular‐biology assay names and experimental methods (e.g. Northern blot, PCR, immuno-analysis).

    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
     caution
    -0.08
    _reduction
    -0.06
     crossword
    -0.06
    ochen
    -0.06
     btnSave
    -0.06
     sugars
    -0.06
    報告
    -0.06
    、と
    -0.06
    Pragma
    -0.06
    /update
    -0.06
    POSITIVE LOGITS
    amaha
    0.08
     avatar
    0.07
     =>
    0.06
     $_
    0.06
     RAID
    0.06
    -spe
    0.06
    υγ
    0.06
    immers
    0.06
    .ToolStrip
    0.06
    "].(
    0.06
    Activations Density 0.047%

    No Known Activations