© 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. 130681
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and anecdotes

    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
    á»Ļng
    -0.07
    uÅŁ
    -0.07
    usb
    -0.07
    enson
    -0.06
    qus
    -0.06
    quia
    -0.06
    -anchor
    -0.06
     ÙħشاÙĩ
    -0.06
    zer
    -0.06
    marshall
    -0.06
    POSITIVE LOGITS
     another
    0.10
     unrelated
    0.09
     confusion
    0.09
     hom
    0.08
    croft
    0.08
     confuse
    0.08
     confusing
    0.08
     Another
    0.07
    another
    0.07
    åı¦
    0.07
    Activations Density 0.021%

    No Known Activations