© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6094
    Prev
    Next
    INDEX
    Explanations

    Internet comments and dialogue

    np_max-act · gemini-2.0-flash

    The neuron is detecting discourse‐level filler or hesitation markers (e.g. “uh,” “um,” “well,” “hmm”) in the transcript.

    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
    baum
    -0.07
    θο
    -0.07
     /*↵
    -0.07
     元
    -0.07
    _small
    -0.07
     TEST
    -0.07
     tùy
    -0.07
     -↵↵
    -0.07
     ordered
    -0.06
    _truth
    -0.06
    POSITIVE LOGITS
     surreal
    0.07
     Степ
    0.07
    letters
    0.07
    âr
    0.06
     metrics
    0.06
    ps
    0.06
     gaussian
    0.06
     Uhr
    0.05
    clk
    0.05
     الاح
    0.05
    Activations Density 0.051%

    No Known Activations