© 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. 84293
    Prev
    Next
    INDEX
    Explanations

    references to lateral or side orientations

    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
    ysz
    -0.08
    @student
    -0.08
     tess
    -0.07
    Äįen
    -0.07
    аниÑĨ
    -0.07
     pari
    -0.07
    ENCIL
    -0.06
     underlying
    -0.06
    صÙĨ
    -0.06
    ëĭµ
    -0.06
    POSITIVE LOGITS
     sides
    0.08
    (side
    0.08
    身
    0.07
    icular
    0.07
    -side
    0.07
    kits
    0.07
    side
    0.07
    wise
    0.07
    elong
    0.07
    ities
    0.06
    Activations Density 0.015%

    No Known Activations