© 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. 17382
    Prev
    Next
    INDEX
    Explanations

    unique words or terms that signify importance or prominence

    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
    oda
    -0.07
    uso
    -0.06
    év
    -0.06
    cher
    -0.06
    latest
    -0.06
    odium
    -0.06
    रण
    -0.06
    fter
    -0.06
    pas
    -0.06
    ynchronization
    -0.06
    POSITIVE LOGITS
    issen
    0.08
    olet
    0.08
    brush
    0.07
    ORED
    0.07
    aupt
    0.07
    atha
    0.07
    .RESULT
    0.07
    illance
    0.07
    æĺĵ
    0.07
    egr
    0.07
    Activations Density 0.030%

    No Known Activations