© 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. 106204
    Prev
    Next
    INDEX
    Explanations

    references to biological research and initiatives

    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
    สว
    -0.06
     proph
    -0.06
    èĽĩ
    -0.06
    辺
    -0.06
    bben
    -0.06
     sworn
    -0.06
    jie
    -0.06
    ationale
    -0.06
    нÑĥÑĤ
    -0.06
    ContextMenu
    -0.06
    POSITIVE LOGITS
     fora
    0.07
    iative
    0.07
     initiative
    0.07
     network
    0.07
     project
    0.07
     Round
    0.07
    uge
    0.07
    986
    0.07
     member
    0.06
     Working
    0.06
    Activations Density 0.030%

    No Known Activations