© 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. 41763
    Prev
    Next
    INDEX
    Explanations

    references to image credit and attributions

    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
    esel
    -0.07
    emd
    -0.07
    ieme
    -0.07
     hos
    -0.07
    zel
    -0.07
    опиÑģ
    -0.07
    echa
    -0.07
     Já
    -0.06
    ivot
    -0.06
    ocos
    -0.06
    POSITIVE LOGITS
    -tone
    0.07
    æ³ī
    0.06
    .unsplash
    0.06
     handjob
    0.06
    .rl
    0.06
    remote
    0.06
     effic
    0.06
     Attribution
    0.06
    deen
    0.06
    .githubusercontent
    0.05
    Activations Density 0.002%

    No Known Activations