© 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. 38912
    Prev
    Next
    INDEX
    Explanations

    sound

    np_max-act · gemini-2.0-flash

    This neuron primarily detects occurrences of the word “sound” (and closely related audio‐tech terms).

    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
     pund
    -0.07
    "});↵
    -0.07
    Ir
    -0.06
    "A
    -0.06
    (ex
    -0.06
     LENG
    -0.06
     IMO
    -0.06
     наход
    -0.06
     Reaper
    -0.06
    utz
    -0.06
    POSITIVE LOGITS
    oslav
    0.07
    owied
    0.07
     sánh
    0.06
                                    
    0.06
    ClickListener
    0.06
    likely
    0.06
     dm
    0.06
    iating
    0.06
     Audio
    0.06
     इल
    0.06
    Activations Density 0.010%

    No Known Activations