© 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. 72892
    Prev
    Next
    INDEX
    Explanations

    communication and expressions of understanding among characters or individuals

    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
    VisualStyle
    -0.07
    _Result
    -0.07
    asc
    -0.07
    akat
    -0.07
    abis
    -0.07
    mare
    -0.07
    atar
    -0.07
    orra
    -0.07
    acus
    -0.06
    ãģ¾ãģļ
    -0.06
    POSITIVE LOGITS
     indication
    0.12
     indications
    0.12
     indicate
    0.12
     indicates
    0.11
     evidence
    0.10
     indicating
    0.10
     hints
    0.09
     indicated
    0.09
     clues
    0.09
     evid
    0.09
    Activations Density 0.049%

    No Known Activations