© 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. 61004
    Prev
    Next
    INDEX
    Explanations

    phrases indicating distance or separation

    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
    -0.10
    arResult
    -0.07
    ÙĬÙĩ
    -0.07
     __("
    -0.07
    اÙĩÙħ
    -0.06
     diam
    -0.06
    slaught
    -0.06
    ì£
    -0.06
    //{{
    -0.06
    awi
    -0.06
    POSITIVE LOGITS
    otics
    0.06
     oneself
    0.06
     cunt
    0.06
    uly
    0.06
     decent
    0.06
     mau
    0.06
    GLOBALS
    0.06
    .tm
    0.06
     certain
    0.06
    aste
    0.06
    Activations Density 0.000%

    No Known Activations