© 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 EvalsExportsinterp-engineNEWAPI 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. 124041
    Prev
    Next
    INDEX
    Explanations

    expressions of personal performance and self-perception

    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
    Wunused
    -0.10
    bler
    -0.09
    ç¹ģ
    -0.08
    ±Ð¾ÑĤ
    -0.08
    ÙĴب
    -0.08
    unto
    -0.08
     vess
    -0.08
    олаг
    -0.08
    ankan
    -0.08
    setFlash
    -0.08
    POSITIVE LOGITS
     show
    0.07
     judges
    0.06
     Episode
    0.06
     segment
    0.06
     YouTube
    0.06
     Lounge
    0.05
     lounge
    0.05
     strategically
    0.05
    Introduced
    0.05
     audition
    0.05
    Activations Density 0.021%

    No Known Activations