© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30790
    Prev
    Next
    INDEX
    Explanations

    files

    np_max-act · gemini-2.0-flash

    This neuron detects mentions or uses of the Python “tarfile” module (i.e. code opening or handling tar archives).

    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
     Lazar
    -0.07
     Hazel
    -0.06
    Oops
    -0.06
     Champion
    -0.06
    …but
    -0.06
     TX
    -0.06
    のが
    -0.06
     Dub
    -0.06
    那样
    -0.06
     bleach
    -0.06
    POSITIVE LOGITS
     estado
    0.07
    rocket
    0.07
     эк
    0.07
     irgend
    0.07
     ماد
    0.06
     vyb
    0.06
    нє
    0.06
    urnal
    0.06
     ate
    0.06
    algo
    0.06
    Activations Density 0.000%

    No Known Activations