© 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. 89115
    Prev
    Next
    INDEX
    Explanations

    references to websites or web-related content and their usage policies

    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
     kullanarak
    -0.08
    -used
    -0.08
    used
    -0.08
    _USED
    -0.07
    utra
    -0.07
     used
    -0.07
    اÙĨت
    -0.07
     Used
    -0.07
    Used
    -0.07
    øre
    -0.07
    POSITIVE LOGITS
    weis
    0.07
    æŃ
    0.07
     cel
    0.07
     res
    0.06
    vel
    0.06
    cel
    0.06
     Ses
    0.06
    vo
    0.06
    esso
    0.06
     ps
    0.06
    Activations Density 0.010%

    No Known Activations