© 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. 75035
    Prev
    Next
    INDEX
    Explanations

    code-related syntax or structural elements

    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
    .scalablytyped
    -0.09
    835
    -0.06
     ple
    -0.06
     Manit
    -0.06
    hare
    -0.06
    285
    -0.06
     Stad
    -0.06
    _PUS
    -0.06
     Harding
    -0.06
    ih
    -0.06
    POSITIVE LOGITS
    è¦ļ
    0.07
     Consort
    0.07
     Mail
    0.06
    limits
    0.06
     stor
    0.06
    unes
    0.06
    elan
    0.06
    mostat
    0.06
    ampie
    0.06
    ازÙĦ
    0.06
    Activations Density 0.001%

    No Known Activations