© 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. 3785
    Prev
    Next
    INDEX
    Explanations

    references to support, care, and inclusivity for individuals with special needs

    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
     spot
    -0.06
    омен
    -0.06
    spot
    -0.06
     Benedict
    -0.06
    \<^
    -0.06
     Lomb
    -0.06
     sacrifices
    -0.06
    ioc
    -0.06
     decl
    -0.06
    erm
    -0.06
    POSITIVE LOGITS
     wheelchair
    0.08
     whe
    0.08
     Whe
    0.08
     mobility
    0.08
    Wheel
    0.08
    wheel
    0.07
    ologne
    0.07
     sensory
    0.07
    -disable
    0.07
     Modifier
    0.07
    Activations Density 0.001%

    No Known Activations