© 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. 5-LLAMASCOPE-RES-131K
    11. 126442
    Prev
    Next
    INDEX
    Explanations

    references to academic citations

    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
    rosso
    -0.09
    ADVERTISEMENT
    -0.08
    PropertyChanged
    -0.07
    ryn
    -0.07
    -regexp
    -0.07
    occo
    -0.07
    adol
    -0.07
    liner
    -0.07
    roud
    -0.07
    ñana
    -0.07
    POSITIVE LOGITS
    iot
    0.06
    atable
    0.06
     FI
    0.05
     Chase
    0.05
     silhouette
    0.05
     Chun
    0.05
     only
    0.05
    yms
    0.05
    700
    0.05
    kelig
    0.05
    Activations Density 0.043%

    No Known Activations