© 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. 38144
    Prev
    Next
    INDEX
    Explanations

    half

    np_max-act · gemini-2.0-flash

    This neuron fires on subword tokens that occur at the beginnings of longer words—that is, it detects word‐initial subword segments.

    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
     jealous
    -0.07
    igr
    -0.07
    Earn
    -0.06
     HV
    -0.06
    _gender
    -0.06
    bot
    -0.06
     Natural
    -0.06
    _AX
    -0.06
    间
    -0.06
     Likely
    -0.06
    POSITIVE LOGITS
    _struct
    0.07
    ψης
    0.06
    (parsed
    0.06
     ''
↵
    0.06
    "go
    0.06
    Devices
    0.06
    /books
    0.06
    curve
    0.06
    _problem
    0.06
    บค
    0.06
    Activations Density 0.258%

    No Known Activations