© 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. 15028
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of individuals and cultural references

    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
    -urlencoded
    -0.07
    ìļ°ë¦¬
    -0.07
    çķ°
    -0.07
    indow
    -0.06
    atic
    -0.06
    agu
    -0.06
    urgence
    -0.06
    agraph
    -0.06
    etails
    -0.06
    ãĥ¬ãĥ¼
    -0.06
    POSITIVE LOGITS
    :
    0.08
    ा:
    0.07
     mee
    0.06
    _-_
    0.06
    itemap
    0.06
    elon
    0.06
    £½
    0.06
     ComVisible
    0.06
    ledon
    0.06
     talk
    0.06
    Activations Density 0.115%

    No Known Activations