© 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. 118924
    Prev
    Next
    INDEX
    Explanations

    references to series or sequences of projects, films, or initiatives

    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
    éri
    -0.07
     plus
    -0.06
    amel
    -0.06
    gif
    -0.06
     alone
    -0.06
    buch
    -0.06
    irc
    -0.06
     instead
    -0.06
     etc
    -0.05
    ’
    -0.05
    POSITIVE LOGITS
    PLICIT
    0.09
    athroom
    0.08
    hetto
    0.07
    odelist
    0.07
    åĿ¡
    0.07
    ActionCreators
    0.07
    inus
    0.07
    abouts
    0.07
    encent
    0.07
    cwd
    0.07
    Activations Density 0.021%

    No Known Activations