© 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 EvalsExportsinterp-engineNEWAPI 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. 62666
    Prev
    Next
    INDEX
    Explanations

    conversational dialogue including requests and responses

    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
    pai
    -0.07
    edBy
    -0.06
    Thunk
    -0.06
    inded
    -0.06
    PostExecute
    -0.06
    ays
    -0.06
     eldre
    -0.06
    aban
    -0.06
    olas
    -0.06
    831
    -0.06
    POSITIVE LOGITS
     instruction
    0.09
     instructions
    0.08
     explan
    0.07
     Instruction
    0.07
    Instructions
    0.06
     инÑģÑĤÑĢÑĥк
    0.06
     Bid
    0.06
    entr
    0.06
    Instruction
    0.06
    ÐľÐŀ
    0.06
    Activations Density 0.039%

    No Known Activations