© 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 EvalsExportsAPI 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. 60905
    Prev
    Next
    INDEX
    Explanations

    connections and integrations between different systems and platforms

    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
    enas
    -0.07
    bish
    -0.07
    LÄ°
    -0.07
    kü
    -0.07
    vik
    -0.07
    ahat
    -0.07
    IndexPath
    -0.07
    áno
    -0.07
     ÙĤØ·
    -0.07
    eos
    -0.07
    POSITIVE LOGITS
     existing
    0.09
     other
    0.08
    existing
    0.08
     altre
    0.07
     Existing
    0.07
     directly
    0.07
     backend
    0.06
     popular
    0.06
     sister
    0.06
    terror
    0.06
    Activations Density 0.025%

    No Known Activations