© 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. 5356
    Prev
    Next
    INDEX
    Explanations

    references to academic or institutional awards and honors

    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
     _
    -0.06
    -0.06
     grave
    -0.06
    ally
    -0.06
    ixels
    -0.06
     included
    -0.06
    aments
    -0.06
    th
    -0.06
    grave
    -0.05
    ops
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.09
    .Criteria
    0.08
     awards
    0.08
    Streamer
    0.08
    ksam
    0.08
    .PropTypes
    0.07
    serter
    0.07
     award
    0.07
    InParameter
    0.07
     memorial
    0.07
    Activations Density 0.020%

    No Known Activations