© 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. 94847
    Prev
    Next
    INDEX
    Explanations

    lists or enumerations, particularly those involving recommendations or actions

    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
    ism
    -0.08
    (_)
    -0.08
    ["$
    -0.07
    âĢ¦↵↵↵
    -0.07
    olumn
    -0.07
    ãģ«ãģĹãģ¦
    -0.07
    ãĢ
    -0.07
    ÙĪب
    -0.07
     –↵↵
    -0.07
    tainment
    -0.07
    POSITIVE LOGITS
    :↵
    0.14
    ):↵
    0.11
    :č↵
    0.10
    :↵↵
    0.09
    ]:↵
    0.09
     :↵
    0.08
    ï¼ļ↵
    0.08
    ;↵
    0.08
    ':↵
    0.07
    ":↵
    0.07
    Activations Density 0.030%

    No Known Activations