© 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. 58935
    Prev
    Next
    INDEX
    Explanations

    directional and positional language related to movement or arrangement

    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
    arel
    -0.07
    åįļ士
    -0.06
    ela
    -0.06
    owed
    -0.06
    avy
    -0.06
    ace
    -0.06
    eworthy
    -0.06
    anna
    -0.06
    IfExists
    -0.06
    aca
    -0.06
    POSITIVE LOGITS
    'icon
    0.07
    /by
    0.07
    /etc
    0.07
    wik
    0.07
    476
    0.06
    ħn
    0.06
     Sto
    0.06
    sto
    0.06
    à¥Ĥत
    0.06
    erro
    0.06
    Activations Density 0.050%

    No Known Activations