© 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. 125663
    Prev
    Next
    INDEX
    Explanations

    references to documentaries

    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
    /operators
    -0.07
    رÙĤ
    -0.07
    ä¸ĸ
    -0.07
    _CONNECTED
    -0.07
    sed
    -0.07
    èŃľ
    -0.07
    ocol
    -0.07
    ses
    -0.07
    ãĥ³ãĥĶ
    -0.07
    _COPY
    -0.07
    POSITIVE LOGITS
    -style
    0.10
    -like
    0.09
    /document
    0.07
    -type
    0.07
    -esque
    0.07
     style
    0.07
     Maker
    0.07
    -grade
    0.06
    like
    0.06
     evidence
    0.06
    Activations Density 0.005%

    No Known Activations