© 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. 15-LLAMASCOPE-RES-131K
    11. 87154
    Prev
    Next
    INDEX
    Explanations

    phrases indicating repetition or emphasis on quantity

    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
    anas
    -0.07
    ìķĻ
    -0.07
    åĴ²
    -0.07
     climax
    -0.06
    iji
    -0.06
     Guns
    -0.06
    nal
    -0.06
    -commercial
    -0.06
    溪
    -0.06
    Constants
    -0.06
    POSITIVE LOGITS
    amespace
    0.07
    ingly
    0.07
    atel
    0.07
    ammer
    0.06
    uario
    0.06
    amac
    0.06
    OGLE
    0.06
    çĵ
    0.06
    ocket
    0.06
    gre
    0.06
    Activations Density 0.004%

    No Known Activations