© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 129605
    Prev
    Next
    INDEX
    Explanations

    expressions related to fixation or preoccupation with a subject or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    manship
    -0.08
    hea
    -0.07
    avis
    -0.07
    stral
    -0.07
    apped
    -0.07
    ispers
    -0.07
    uspend
    -0.07
    oji
    -0.07
    erness
    -0.07
    ning
    -0.07
    POSITIVE LOGITS
    ively
    0.09
    -comp
    0.08
    oso
    0.08
    ingly
    0.07
    225
    0.07
     obs
    0.07
     compuls
    0.06
     minded
    0.06
    念
    0.06
    ably
    0.06
    Activations Density 0.007%

    No Known Activations