© 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. 18387
    Prev
    Next
    INDEX
    Explanations

    URLs and hyperlinks

    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
    ibel
    -0.07
    urger
    -0.07
    ede
    -0.06
    isay
    -0.06
    urent
    -0.06
    onom
    -0.06
    regor
    -0.06
    azor
    -0.06
    lest
    -0.06
    ulo
    -0.06
    POSITIVE LOGITS
    ê±°ëŀĺê°Ģ
    0.07
    ếu
    0.07
    ÑĢаниÑĨ
    0.07
    AGER
    0.07
    çŃĴ
    0.06
    æ¯
    0.06
    kü
    0.06
     INTERRU
    0.06
    è¡Ŀ
    0.06
    _ALIAS
    0.06
    Activations Density 0.001%

    No Known Activations