© 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. 29808
    Prev
    Next
    INDEX
    Explanations

    file paths

    np_max-act · gemini-2.0-flash

    technical configurations or error messages related to software development environments.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on pieces of file‐system paths (e.g. drive letters, directory names, and separators in absolute path strings).

    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
    ipa
    -0.06
     sop
    -0.06
    .ar
    -0.06
    xDE
    -0.06
    Verse
    -0.06
     Agriculture
    -0.06
    кий
    -0.06
     Paladin
    -0.06
    ्ह
    -0.06
     imageName
    -0.06
    POSITIVE LOGITS
    /providers
    0.07
    ….↵↵
    0.06
     για
    0.06
    )).↵
    0.06
     Monkey
    0.06
     MMP
    0.06
     با
    0.06
    .↵↵
    0.06
    .↵
    0.06
     dk
    0.06
    Activations Density 0.014%

    No Known Activations