© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 75702
    Prev
    Next
    INDEX
    Explanations

    mentions of library files or dependencies in programming contexts

    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
    ottage
    -0.06
    anke
    -0.06
    amat
    -0.06
    ÙĤÛĮ
    -0.06
    enga
    -0.06
    vincia
    -0.06
    ắn
    -0.06
    ivic
    -0.06
    íĹĪ
    -0.06
    stu
    -0.06
    POSITIVE LOGITS
    ardown
    0.07
    /native
    0.06
    rior
    0.06
    depend
    0.06
    664
    0.06
    upa
    0.06
    /../
    0.06
    neapolis
    0.06
     Daly
    0.06
    NEG
    0.06
    Activations Density 0.001%

    No Known Activations