© 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. 29003
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a quantity or reference a group

    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
    uch
    -0.08
    /loose
    -0.07
    anders
    -0.06
    ande
    -0.06
    eg
    -0.06
    xin
    -0.06
    ViewState
    -0.06
     autorelease
    -0.06
    زÙĩ
    -0.06
    аÑĢан
    -0.05
    POSITIVE LOGITS
     others
    0.14
    others
    0.13
     Others
    0.11
    Others
    0.11
     alike
    0.09
     names
    0.07
     whose
    0.07
     contempor
    0.07
     countless
    0.07
    imitives
    0.07
    Activations Density 0.022%

    No Known Activations