© 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. 85348
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantities or comparisons

    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
     slightly
    -0.07
    ÙĨب
    -0.07
    .↵↵↵↵↵↵↵↵↵↵
    -0.06
    Ä°s
    -0.06
    eree
    -0.06
    ivel
    -0.06
    ighton
    -0.06
    ÑĤаб
    -0.06
    ednou
    -0.06
     –↵↵
    -0.06
    POSITIVE LOGITS
     or
    0.12
     sometimes
    0.11
     even
    0.10
    çĶļèĩ³
    0.10
    sometimes
    0.09
     multiple
    0.08
     hatta
    0.08
    even
    0.08
     oder
    0.08
     hundreds
    0.07
    Activations Density 0.033%

    No Known Activations