© 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. 1738
    Prev
    Next
    INDEX
    Explanations

    non-standard characters or symbols often used in encoding or special text formatting

    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
    964
    -0.07
    erson
    -0.06
     Bez
    -0.06
    ement
    -0.06
    atur
    -0.06
     Baghd
    -0.06
    /column
    -0.06
    izz
    -0.06
    ATAR
    -0.06
    isy
    -0.06
    POSITIVE LOGITS
    ī
    0.08
    ³
    0.08
    ¥
    0.07
    marshall
    0.07
    ï¸
    0.07
     Piper
    0.06
    ĩ
    0.06
    Ĥ
    0.06
    ļ
    0.06
    ãĤĿ
    0.06
    Activations Density 0.001%

    No Known Activations