© 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. 15-LLAMASCOPE-RES-131K
    11. 90096
    Prev
    Next
    INDEX
    Explanations

    terminology related to chemical processes and compositions

    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
    odom
    -0.07
    agy
    -0.07
    orsi
    -0.07
    conti
    -0.07
    éĩ
    -0.07
     otherwise
    -0.07
    tÃŃ
    -0.07
    olley
    -0.07
     EXEMPLARY
    -0.07
    amel
    -0.06
    POSITIVE LOGITS
     tzv
    0.07
     various
    0.07
    .truth
    0.06
    .setViewport
    0.06
    ADDE
    0.06
    ãģ°
    0.06
    ximity
    0.06
     Kare
    0.06
    ìļ´
    0.06
     ÅĻada
    0.06
    Activations Density 0.037%

    No Known Activations