© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87316
    Prev
    Next
    INDEX
    Explanations

    actions related to movement or stepping

    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
    DRAM
    -0.08
    istrat
    -0.08
    tir
    -0.07
    éļ
    -0.07
    ouver
    -0.07
    letal
    -0.07
    oblin
    -0.07
    kw
    -0.07
    azers
    -0.07
     è¡ĮæĶ¿
    -0.07
    POSITIVE LOGITS
     toes
    0.09
     foot
    0.09
     footprint
    0.08
    è¸ı
    0.07
    foot
    0.07
    -foot
    0.07
     ног
    0.07
     pedal
    0.07
    Foot
    0.07
    idis
    0.06
    Activations Density 0.018%

    No Known Activations