© 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. 56048
    Prev
    Next
    INDEX
    Explanations

    specific software applications and technological solutions

    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
    riad
    -0.07
    usk
    -0.07
     McCart
    -0.06
    thy
    -0.06
    yang
    -0.06
    rap
    -0.06
    yer
    -0.06
     Proud
    -0.06
    Äħd
    -0.06
    ibt
    -0.06
    POSITIVE LOGITS
     there
    0.09
     you
    0.09
     we
    0.07
    нод
    0.07
    there
    0.07
    ï¼Įä½ł
    0.06
     você
    0.06
    you
    0.06
     ä½ł
    0.06
     setattr
    0.06
    Activations Density 0.018%

    No Known Activations