© 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. 42929
    Prev
    Next
    INDEX
    Explanations

    Code/file references

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric identifier tokens (e.g. version numbers and object/file reference IDs) in the build-file.

    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
     Leban
    -0.06
    (version
    -0.06
    ео
    -0.06
    ngoing
    -0.06
    AK
    -0.06
    (ap
    -0.06
    cím
    -0.06
    _inactive
    -0.05
    URES
    -0.05
    akin
    -0.05
    POSITIVE LOGITS
     Streets
    0.08
    .Schema
    0.07
     StringType
    0.07
     gag
    0.06
     shredd
    0.06
     ];
    0.06
     उच
    0.06
     drifting
    0.06
     Redistribution
    0.06
     Darth
    0.06
    Activations Density 0.003%

    No Known Activations