© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 86995
    Prev
    Next
    INDEX
    Explanations

    phrases indicating collaboration and support for projects or ideas

    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
    337
    -0.07
    abase
    -0.07
    ï¼Ł
    -0.07
    .builders
    -0.07
    лим
    -0.06
    ï¼Ł↵
    -0.06
    \-
    -0.06
    ëį°ìĿ´íĬ¸
    -0.06
    izon
    -0.06
    \<^
    -0.06
    POSITIVE LOGITS
    conditionally
    0.07
    osu
    0.07
    cht
    0.07
    ields
    0.07
    assi
    0.07
    ebra
    0.07
    apesh
    0.06
    ourmet
    0.06
    ratulations
    0.06
    cid
    0.06
    Activations Density 0.048%

    No Known Activations