© 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. 9-LLAMASCOPE-RES-131K
    11. 96779
    Prev
    Next
    INDEX
    Explanations

    numeric references or indexes related to sequences or lists

    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
    aña
    -0.07
    osten
    -0.07
    ultur
    -0.07
    raft
    -0.07
    urovision
    -0.06
    amic
    -0.06
    imson
    -0.06
    rette
    -0.06
    orge
    -0.06
    adder
    -0.06
    POSITIVE LOGITS
     Whites
    0.07
     Hour
    0.06
     вза
    0.06
    تÙĪÙĨ
    0.06
    æĽ
    0.06
    otation
    0.06
     Egg
    0.06
    Neutral
    0.06
    _DIP
    0.05
     underwater
    0.05
    Activations Density 0.043%

    No Known Activations