© 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. 29325
    Prev
    Next
    INDEX
    Explanations

    exception handling and error-related keywords

    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
    ¶Į
    -0.08
     ÙģرÙĪ
    -0.08
    ulo
    -0.07
    voj
    -0.07
    isd
    -0.07
     extravag
    -0.07
    ÃŃsk
    -0.07
    owie
    -0.06
    afen
    -0.06
    èįī
    -0.06
    POSITIVE LOGITS
    otics
    0.06
    ("
    0.06
    RLF
    0.06
    даÑĤ
    0.06
    rowable
    0.06
    nameof
    0.06
    semble
    0.05
    ayla
    0.05
    aire
    0.05
    locker
    0.05
    Activations Density 0.007%

    No Known Activations