© 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. 79413
    Prev
    Next
    INDEX
    Explanations

    references to visual elements or imagery

    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
    ãģĤãģ®
    -0.08
    enas
    -0.07
    readcr
    -0.07
     sublic
    -0.07
    ters
    -0.07
    enic
    -0.07
    akis
    -0.06
    iedade
    -0.06
    hand
    -0.06
    anism
    -0.06
    POSITIVE LOGITS
    iting
    0.09
    ually
    0.08
    cosity
    0.08
    (vis
    0.08
     versa
    0.08
    quel
    0.08
     Vis
    0.08
    -vis
    0.08
    ory
    0.07
    UAL
    0.07
    Activations Density 0.021%

    No Known Activations