© 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. 9-LLAMASCOPE-RES-131K
    11. 97078
    Prev
    Next
    INDEX
    Explanations

    references to user interface components in software development

    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
    ieu
    -0.08
    ieur
    -0.06
     abs
    -0.06
    968
    -0.06
    673
    -0.06
    ale
    -0.06
    rom
    -0.06
    pak
    -0.06
    889
    -0.06
     Brennan
    -0.05
    POSITIVE LOGITS
    aday
    0.08
     vidéos
    0.08
    GIN
    0.07
     acomp
    0.07
    ëĵľë¦¬
    0.07
     automát
    0.07
    аÑĢÑĸ
    0.07
    IDI
    0.07
    ETHOD
    0.07
    ECTOR
    0.07
    Activations Density 0.006%

    No Known Activations