© 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. 12292
    Prev
    Next
    INDEX
    Explanations

    want, desire

    np_max-act · gemini-2.0-flash

    This neuron detects phrasing where the user expresses a desire for information, as in “like to know about.”

    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
    Arrow
    -0.07
    \xf
    -0.07
     tumult
    -0.06
    eníze
    -0.06
    ReturnValue
    -0.06
     ngờ
    -0.06
     Blanc
    -0.06
    之前
    -0.06
    incl
    -0.06
    év
    -0.06
    POSITIVE LOGITS
     assertTrue
    0.07
     tumble
    0.06
     اخلاق
    0.06
     ay
    0.06
     ima
    0.06
    .Css
    0.06
    .host
    0.06
    .Send
    0.06
     pains
    0.06
    aims
    0.06
    Activations Density 0.016%

    No Known Activations