© 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. 1145
    Prev
    Next
    INDEX
    Explanations

    phrases related to competition and performance metrics

    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
    urai
    -0.07
    olec
    -0.07
    arkin
    -0.07
     Gos
    -0.06
    onden
    -0.06
    atto
    -0.06
     Remaining
    -0.06
    utow
    -0.06
    icro
    -0.06
    igne
    -0.06
    POSITIVE LOGITS
     improvement
    0.08
     improves
    0.07
     worse
    0.07
     improve
    0.07
     å°
    0.07
     mejorar
    0.07
     Improve
    0.07
    orsche
    0.07
     Improvement
    0.07
     improvements
    0.07
    Activations Density 0.065%

    No Known Activations