© 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. 106702
    Prev
    Next
    INDEX
    Explanations

    specific references to structures and resources in a community

    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
    leans
    -0.08
    raya
    -0.07
    orta
    -0.07
    NESS
    -0.07
    ainen
    -0.07
    gie
    -0.07
    eldorf
    -0.07
    juan
    -0.07
    etik
    -0.07
    utsch
    -0.07
    POSITIVE LOGITS
     various
    0.07
     yandan
    0.07
     trunk
    0.06
     Beg
    0.06
    leading
    0.05
    ((-
    0.05
    ÙĪرات
    0.05
     Nová
    0.05
     springfox
    0.05
    407
    0.05
    Activations Density 0.080%

    No Known Activations