© 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. 43197
    Prev
    Next
    INDEX
    Explanations

    new perspectives

    np_max-act · gemini-2.0-flash

    This neuron detects section or article titles that begin with “New” (e.g. “A New Perspective,” “A New Take on …”)—i.e. tokens in “New …” title phrases.

    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
     proceeds
    -0.06
     followed
    -0.06
     Angebot
    -0.06
    What
    -0.06
     Mehr
    -0.06
    .NONE
    -0.06
     interrupted
    -0.06
     favoured
    -0.06
     copied
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    removeClass
    0.08
     Gallery
    0.07
    Persistent
    0.07
    itory
    0.07
     Flooring
    0.07
     athleticism
    0.07
    raise
    0.07
     mastur
    0.07
    TokenType
    0.06
    -stats
    0.06
    Activations Density 0.033%

    No Known Activations