© 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. 61054
    Prev
    Next
    INDEX
    Explanations

    references to past experiences and memories

    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
     wait
    -0.07
    llib
    -0.07
    _wait
    -0.07
    .Wait
    -0.07
     Maul
    -0.07
    ÙĪÙĦÛĮ
    -0.07
     lifelong
    -0.07
    arkan
    -0.07
    olare
    -0.06
    ÑĢÑĥж
    -0.06
    POSITIVE LOGITS
    uzzi
    0.08
     gal
    0.07
    uhn
    0.06
     properly
    0.06
     anything
    0.06
    ignon
    0.06
    羣æŃ£
    0.06
    å°¼äºļ
    0.06
     truly
    0.06
     bon
    0.06
    Activations Density 0.006%

    No Known Activations