© 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. 124748
    Prev
    Next
    INDEX
    Explanations

    ell

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting the beginnings (prefixes) of longer, domain-specific technical or scientific terms.

    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
    Bl
    -0.07
    Stars
    -0.07
    (CC
    -0.07
    Software
    -0.07
    Ws
    -0.07
    ष
    -0.07
    _ignore
    -0.07
     вероят
    -0.07
    iginal
    -0.07
    Nullable
    -0.06
    POSITIVE LOGITS
     hier
    0.06
    errorCode
    0.06
     effective
    0.06
     bal
    0.06
    ensely
    0.06
     disadv
    0.06
     autob
    0.06
    _INTERVAL
    0.05
    UIApplicationDelegate
    0.05
     explanation
    0.05
    Activations Density 0.157%

    No Known Activations