© 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. 17-LLAMASCOPE-RES-131K
    11. 77307
    Prev
    Next
    INDEX
    Explanations

    descriptors of unique locations and experiences

    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
    xcd
    -0.07
    ptune
    -0.06
    æĤª
    -0.06
    odable
    -0.06
    283
    -0.06
    231
    -0.06
    warts
    -0.06
    aghan
    -0.06
     ~>
    -0.06
    abbo
    -0.06
    POSITIVE LOGITS
     dÃłi
    0.10
    long
    0.10
    -long
    0.10
    evity
    0.10
    ueur
    0.09
     long
    0.09
    term
    0.09
    ,long
    0.09
     LONG
    0.08
    -term
    0.08
    Activations Density 0.045%

    No Known Activations