© 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. 54390
    Prev
    Next
    INDEX
    Explanations

    keywords and identifiers related to academic or research citations

    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
    ávÄĽ
    -0.06
    ç¬Ķ
    -0.06
    .)↵↵↵↵
    -0.05
    اÙħÙĩ
    -0.05
    ÅĻ
    -0.05
    ÇIJ
    -0.05
    13
    -0.05
     æī
    -0.05
    ợ
    -0.05
    ¨
    -0.05
    POSITIVE LOGITS
    202
    0.18
    Û²Û°Û²
    0.12
     COVID
    0.09
    кÑĥлÑı
    0.08
    201
    0.08
     Covid
    0.08
    SGlobal
    0.08
     ActionTypes
    0.08
     covid
    0.08
    IIIK
    0.08
    Activations Density 0.017%

    No Known Activations