© 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. 15-LLAMASCOPE-RES-131K
    11. 88318
    Prev
    Next
    INDEX
    Explanations

    specific mathematical and programming expressions or constructs

    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
    erk
    -0.08
    enthal
    -0.07
    pak
    -0.07
    asl
    -0.07
    pdata
    -0.07
    dummy
    -0.06
    æĤł
    -0.06
    ï¼Ĩ
    -0.06
    è¡Ĺ
    -0.06
    TPL
    -0.06
    POSITIVE LOGITS
    upo
    0.06
    VG
    0.06
    ì§ģ
    0.06
     elkaar
    0.05
    reas
    0.05
     refinery
    0.05
    urai
    0.05
    auge
    0.05
    ascus
    0.05
    lsen
    0.05
    Activations Density 0.069%

    No Known Activations