© 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. 130486
    Prev
    Next
    INDEX
    Explanations

    references to academic challenges and support systems

    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
    hue
    -0.08
    MOD
    -0.07
     MOD
    -0.07
    ılı
    -0.06
    SOR
    -0.06
    oler
    -0.06
    Å¡e
    -0.06
    amaz
    -0.06
    VML
    -0.06
    esel
    -0.06
    POSITIVE LOGITS
     career
    0.10
    career
    0.09
     careers
    0.09
     Career
    0.08
     unten
    0.07
     NIH
    0.07
     Careers
    0.07
     grad
    0.07
    maal
    0.07
    ipp
    0.07
    Activations Density 0.095%

    No Known Activations