© 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. 43234
    Prev
    Next
    INDEX
    Explanations

    DNS lookup failures

    np_max-act · gemini-2.0-flash

    The neuron activates on DNS‐specific technical terms—words naming protocol operations, configuration objects, or record types (e.g. “query,” “zone,” “RRs,” “bind,” etc.).

    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
     CFR
    -0.06
     Economic
    -0.06
    _Show
    -0.06
    _REPORT
    -0.06
    决定
    -0.06
    Paste
    -0.06
    IGN
    -0.06
    FR
    -0.06
    จาก
    -0.06
     IND
    -0.06
    POSITIVE LOGITS
    	item
    0.07
     Nullable
    0.07
     ;;=
    0.07
    ryan
    0.07
    ixer
    0.07
    .Theme
    0.07
    setImage
    0.06
     Vive
    0.06
    ิดต
    0.06
    ;:;:
    0.06
    Activations Density 0.006%

    No Known Activations