© 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 EvalsExportsAPI 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. 16560
    Prev
    Next
    INDEX
    Explanations

    specific downloadable content or resources, such as images, documents, and tools

    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
     clue
    -0.07
    dash
    -0.06
    apy
    -0.06
    aea
    -0.06
    ateg
    -0.06
    osas
    -0.06
    anken
    -0.06
    νι
    -0.06
     Inputs
    -0.06
    quals
    -0.06
    POSITIVE LOGITS
     onto
    0.13
    onto
    0.13
    into
    0.08
     unto
    0.08
    from
    0.08
     Ont
    0.07
     into
    0.07
     from
    0.07
    ioc
    0.07
    ä¸ĭæĿ¥
    0.07
    Activations Density 0.020%

    No Known Activations