© 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. 2922
    Prev
    Next
    INDEX
    Explanations

    terms related to assistance and support

    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
    elpers
    -0.08
    utton
    -0.08
    487
    -0.07
    iye
    -0.07
    uchen
    -0.07
    ë¨
    -0.07
    _help
    -0.06
    rier
    -0.06
    urette
    -0.06
    uer
    -0.06
    POSITIVE LOGITS
    lessly
    0.06
    desk
    0.06
    allas
    0.06
    lessness
    0.06
     me
    0.06
    ovat
    0.06
    Desk
    0.06
    enant
    0.05
    incer
    0.05
    upos
    0.05
    Activations Density 0.007%

    No Known Activations