© 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 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. 38921
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    This neuron detects liability‐ and responsibility‐disclaimer language (e.g. “not responsible for,” “liable for,” “without warranty”).

    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
    خب
    -0.08
     JK
    -0.07
     dữ
    -0.07
     HEX
    -0.06
    vor
    -0.06
    ertime
    -0.06
     яс
    -0.06
     anim
    -0.06
     Alone
    -0.06
    .reload
    -0.06
    POSITIVE LOGITS
     }
↵
↵
↵
↵
    0.08
    .'</
    0.06
    _weights
    0.06
    FunctionFlags
    0.06
     getResources
    0.06
     ReturnType
    0.06
     SKF
    0.06
     @(
    0.06
     xtype
    0.06
     професій
    0.06
    Activations Density 0.003%

    No Known Activations