© 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. 130671
    Prev
    Next
    INDEX
    Explanations

    concepts related to borrowing and accessing digital content

    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
     daytime
    -0.07
    APT
    -0.07
    anja
    -0.07
     Typed
    -0.07
    imeo
    -0.07
    Periph
    -0.07
    _Word
    -0.06
    _categorical
    -0.06
    byss
    -0.06
    uraa
    -0.06
    POSITIVE LOGITS
     purchase
    0.06
    wig
    0.06
    illin
    0.06
     household
    0.06
     Sou
    0.06
     transc
    0.06
    rip
    0.06
    annie
    0.06
     entitlement
    0.06
    asons
    0.06
    Activations Density 0.007%

    No Known Activations