© 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. 29011
    Prev
    Next
    INDEX
    Explanations

    references to expectations and outcomes related to success or performance

    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
    isson
    -0.07
    esi
    -0.07
    &E
    -0.06
    antee
    -0.06
    overrides
    -0.06
    osi
    -0.06
    é»İ
    -0.06
     Bang
    -0.06
     herk
    -0.06
    alphabet
    -0.06
    POSITIVE LOGITS
    /time
    0.08
    çļĦä¸Ģ个
    0.07
    ancellable
    0.07
    ëĮĢë¡ľ
    0.06
    wert
    0.06
    ousel
    0.06
    /high
    0.06
    enville
    0.06
    582
    0.06
     Hague
    0.06
    Activations Density 0.020%

    No Known Activations