© 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. 58797
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric tokens containing decimal points (e.g., docket or reference numbers with a decimal).

    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
    heet
    -0.06
    .gf
    -0.06
     �
    -0.06
    افق
    -0.06
    .mc
    -0.06
    redicate
    -0.06
    _MAXIMUM
    -0.06
    Bullet
    -0.06
     nutrit
    -0.06
     FS
    -0.06
    POSITIVE LOGITS
    Whatever
    0.09
     Whatever
    0.07
     heav
    0.07
    whatever
    0.07
    .setData
    0.07
     menj
    0.07
    getFullYear
    0.06
     Bot
    0.06
    無し
    0.06
    JV
    0.06
    Activations Density 0.007%

    No Known Activations