© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 39769
    Prev
    Next
    INDEX
    Explanations

    acknowledgments and recognition in various 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
    eg
    -0.05
    Ñĩив
    -0.05
     respectively
    -0.05
    ainties
    -0.05
    Ñħодим
    -0.04
    óż
    -0.04
     //-
    -0.04
    arring
    -0.04
    ensely
    -0.04
    iable
    -0.04
    POSITIVE LOGITS
     also
    0.44
    also
    0.39
    Also
    0.37
     Also
    0.36
     ALSO
    0.34
     ÑĤакже
    0.31
     juga
    0.31
     también
    0.31
     também
    0.30
     cũng
    0.29
    Activations Density 0.589%

    No Known Activations