© 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. 120291
    Prev
    Next
    INDEX
    Explanations

    terminology and concepts associated with industry dynamics and challenges

    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
    amb
    -0.08
     çł
    -0.07
    è¡Ĺ
    -0.06
    reserve
    -0.06
    wart
    -0.06
    xo
    -0.06
     Presence
    -0.06
    abit
    -0.06
    lying
    -0.06
     amb
    -0.06
    POSITIVE LOGITS
     Profession
    0.09
     colleagues
    0.08
     profession
    0.08
     colleague
    0.08
     gratuiti
    0.08
     ourselves
    0.07
    igator
    0.07
    profession
    0.07
    afc
    0.07
     practitioners
    0.07
    Activations Density 0.092%

    No Known Activations