© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78293
    Prev
    Next
    INDEX
    Explanations

    elements related to geometric and mathematical operations involving shapes and points

    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
    azen
    -0.07
    CHED
    -0.07
    ahat
    -0.07
    .extensions
    -0.07
    Č↵
    -0.07
    deaux
    -0.07
    rippling
    -0.07
    ÙıÙĪا
    -0.07
    æ·»
    -0.07
    icone
    -0.06
    POSITIVE LOGITS
     final
    0.07
     ple
    0.07
    final
    0.07
    apl
    0.06
     UNUSED
    0.06
     Hind
    0.06
    asp
    0.05
     abstract
    0.05
    igr
    0.05
     proportional
    0.05
    Activations Density 0.018%

    No Known Activations