© 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. 107712
    Prev
    Next
    INDEX
    Explanations

    references to text processing functions in programming

    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
    uber
    -0.09
    erman
    -0.08
    orro
    -0.08
    876
    -0.07
    et
    -0.07
    erset
    -0.06
    ocol
    -0.06
    ãĥ¬ãĤ¤
    -0.06
    utenberg
    -0.06
    ilo
    -0.06
    POSITIVE LOGITS
    agento
    0.07
    ISHED
    0.07
    ITS
    0.07
    ãĥ½
    0.06
    "indices
    0.06
    åŃĿ
    0.06
     Richards
    0.06
    /REC
    0.06
    ricks
    0.06
    íĮ¨
    0.06
    Activations Density 0.000%

    No Known Activations