© 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. 61960
    Prev
    Next
    INDEX
    Explanations

    references to libraries and their operations

    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
     unfortunately
    -0.09
     sadly
    -0.08
    Sadly
    -0.07
    Unfortunately
    -0.07
     Sadly
    -0.07
     Unfortunately
    -0.06
     downside
    -0.06
     tiế
    -0.06
    uhn
    -0.06
    ayah
    -0.06
    POSITIVE LOGITS
     remedy
    0.15
     solution
    0.15
     solutions
    0.14
     íķ´ê²°
    0.13
     SOLUTION
    0.13
     remedies
    0.13
     workaround
    0.12
    solution
    0.12
    解åĨ³
    0.11
     Solution
    0.11
    Activations Density 0.128%

    No Known Activations