© 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. 94708
    Prev
    Next
    INDEX
    Explanations

    entities and references related to organizational structures and group memberships

    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
     three
    -0.15
     Three
    -0.14
     trio
    -0.14
    three
    -0.13
     THREE
    -0.13
    Three
    -0.12
     trois
    -0.11
    3
    -0.11
    -three
    -0.11
     threesome
    -0.11
    POSITIVE LOGITS
    ?,?,?,?,
    0.11
     ä¸ĥ
    0.10
    ä¸ĥ
    0.09
    seven
    0.09
     Seven
    0.09
    Seven
    0.09
    ï¼Ĺ
    0.09
     seven
    0.09
     seventh
    0.08
    7
    0.08
    Activations Density 0.020%

    No Known Activations