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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57606
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash

    This neuron activates on terms that refer to quantitative scientific measurements or properties (e.g., “properties,” “activity,” “coverage,” “concentrations,” “structure,” “function,” “vessels,” etc.) in technical or research contexts.

    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
    fin
    -0.06
     precious
    -0.06
     Ν
    -0.06
     dictated
    -0.06
    etCode
    -0.06
    209
    -0.06
    layer
    -0.06
     North
    -0.06
    journal
    -0.06
     Truth
    -0.06
    POSITIVE LOGITS
        ↵↵↵
    0.07
    'post
    0.07
     Approx
    0.07
     ​​
    0.07
     остан
    0.07
     nye
    0.06
     FIG
    0.06
     cbd
    0.06
    unsqueeze
    0.06
     běž
    0.06
    Activations Density 0.149%

    No Known Activations