© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 128719
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or craving for more of something

    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
    AGO
    -0.08
    stile
    -0.07
    alk
    -0.07
    iyim
    -0.07
    weise
    -0.07
     Dün
    -0.07
    èĨ
    -0.07
    측
    -0.06
    UNCH
    -0.06
     HttpServlet
    -0.06
    POSITIVE LOGITS
     of
    0.06
    /to
    0.06
     Vox
    0.06
    uster
    0.06
    ologne
    0.06
    udit
    0.06
    hx
    0.06
     Nobel
    0.06
    rier
    0.05
    ubbo
    0.05
    Activations Density 0.010%

    No Known Activations