© 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. 81793
    Prev
    Next
    INDEX
    Explanations

    phrases indicating involvement in academic or professional programs and affiliations

    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
    deen
    -0.06
    896
    -0.06
    £
    -0.05
    jez
    -0.05
    iang
    -0.05
     Jury
    -0.05
     AMS
    -0.05
    asing
    -0.05
     Lego
    -0.05
     stuff
    -0.05
    POSITIVE LOGITS
     ours
    0.13
     our
    0.12
     nosso
    0.09
    æĪij们çļĦ
    0.09
     наÑĪей
    0.08
     us
    0.08
     nosotros
    0.08
     unserer
    0.08
     unseren
    0.08
     nossa
    0.08
    Activations Density 0.034%

    No Known Activations