© 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. 131055
    Prev
    Next
    INDEX
    Explanations

    information related to grass and its characteristics

    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
    TTY
    -0.06
    antity
    -0.06
    799
    -0.06
    387
    -0.06
     permalink
    -0.06
    bilir
    -0.06
     báo
    -0.06
    otto
    -0.06
     names
    -0.05
     Hipp
    -0.05
    POSITIVE LOGITS
    vig
    0.08
    oga
    0.07
    æ±
    0.07
    Partition
    0.07
     phenotype
    0.07
    zyst
    0.07
    kes
    0.07
    ipy
    0.06
    isy
    0.06
    ocha
    0.06
    Activations Density 0.010%

    No Known Activations