© 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. 104468
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and its various applications

    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
    ĶåĽŀ
    -0.08
    arend
    -0.07
    æīķ
    -0.07
    oretical
    -0.07
    udio
    -0.07
    uilder
    -0.07
    htable
    -0.07
    ounge
    -0.07
    osterone
    -0.07
    eker
    -0.07
    POSITIVE LOGITS
    im
    0.07
    ics
    0.07
    ar
    0.06
    ymous
    0.06
    ạt
    0.06
    eres
    0.06
    nier
    0.06
    ther
    0.06
    c
    0.06
    ycin
    0.06
    Activations Density 0.033%

    No Known Activations