© 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. 106712
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate comparisons or transformations

    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
    /generated
    -0.06
    यर
    -0.06
     TextAlign
    -0.06
    orget
    -0.06
    aÅĻ
    -0.06
    Unified
    -0.06
    opleft
    -0.06
    æĤ
    -0.06
    横
    -0.06
    享
    -0.06
    POSITIVE LOGITS
     full
    0.19
     actual
    0.18
     entire
    0.17
     whole
    0.15
     complete
    0.15
    /full
    0.15
    actual
    0.14
    å®Įæķ´
    0.14
     Actual
    0.14
    full
    0.14
    Activations Density 0.056%

    No Known Activations