© 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. 55216
    Prev
    Next
    INDEX
    Explanations

    parentheses and brackets

    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
    inas
    -0.09
    ứt
    -0.08
    販
    -0.07
    pag
    -0.07
    æ¦
    -0.07
    emoc
    -0.07
    ülü
    -0.07
    asio
    -0.07
    _PARTITION
    -0.07
    æĪ¸
    -0.07
    POSITIVE LOGITS
    -bin
    0.06
     opposite
    0.06
    enville
    0.06
    PK
    0.05
     behind
    0.05
    oz
    0.05
     bas
    0.05
     emphasis
    0.05
     accurately
    0.05
    885
    0.05
    Activations Density 0.003%

    No Known Activations