© 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. 106607
    Prev
    Next
    INDEX
    Explanations

    references to past actions or experiences

    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
    æĥ
    -0.06
    alic
    -0.06
    sworth
    -0.06
     Spotlight
    -0.06
    ersonic
    -0.06
    ube
    -0.06
    окÑĥ
    -0.06
    udos
    -0.06
    ucid
    -0.06
    jev
    -0.06
    POSITIVE LOGITS
    óng
    0.07
    ISA
    0.06
    UA
    0.06
    529
    0.06
    528
    0.06
    iche
    0.06
    unce
    0.06
    pected
    0.06
    dum
    0.06
    oggler
    0.06
    Activations Density 0.004%

    No Known Activations