© 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. 40552
    Prev
    Next
    INDEX
    Explanations

    references to scientific journals and publications

    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
    _compress
    -0.08
    lining
    -0.07
    argin
    -0.07
    arih
    -0.07
    arme
    -0.07
    occo
    -0.07
    aryawan
    -0.07
     Mach
    -0.07
     Proper
    -0.07
    ulous
    -0.06
    POSITIVE LOGITS
    UrlParser
    0.07
    templ
    0.07
    ump
    0.06
    /epl
    0.06
    ACS
    0.06
     Kürt
    0.06
    Scheme
    0.06
     Reaction
    0.06
    _vlog
    0.06
     ACS
    0.06
    Activations Density 0.015%

    No Known Activations