© 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. 86693
    Prev
    Next
    INDEX
    Explanations

    mentions of permissions and restrictions regarding usage rights

    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
    Äĥn
    -0.08
    ÑģÑİ
    -0.07
    cobra
    -0.07
    aney
    -0.07
    gow
    -0.07
    illisecond
    -0.07
    rello
    -0.07
    اساÙĨ
    -0.07
    ÄĽst
    -0.07
    crud
    -0.07
    POSITIVE LOGITS
     prior
    0.07
     our
    0.06
    ique
    0.06
    ster
    0.06
     Mol
    0.05
     express
    0.05
     hierarchy
    0.05
    ÃŃr
    0.05
     axis
    0.05
    ooke
    0.05
    Activations Density 0.002%

    No Known Activations