© 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. 15-LLAMASCOPE-RES-131K
    11. 88628
    Prev
    Next
    INDEX
    Explanations

    references to physical fixtures or components

    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
    -0.09
    ertz
    -0.08
    ethyst
    -0.08
    nt
    -0.07
    ish
    -0.07
    lier
    -0.07
    bies
    -0.07
    (er
    -0.07
    -fashioned
    -0.07
    /is
    -0.07
    POSITIVE LOGITS
    ously
    0.09
    ek
    0.08
    inct
    0.07
    기ê°Ħ
    0.07
    eland
    0.07
    eph
    0.07
    .detectChanges
    0.07
    lád
    0.07
    YPRE
    0.07
    scopic
    0.07
    Activations Density 0.010%

    No Known Activations