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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 39843
    Prev
    Next
    INDEX
    Explanations

    instances of the word "spread" and its derivatives in various contexts

    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
     whom
    -0.06
    ISE
    -0.06
     æŃ
    -0.06
    cassert
    -0.06
     standpoint
    -0.06
     toy
    -0.05
    iscard
    -0.05
     or
    -0.05
     toys
    -0.05
    लत
    -0.05
    POSITIVE LOGITS
     spread
    0.10
    spread
    0.09
     spreading
    0.09
     Spread
    0.09
    vertime
    0.09
    Spread
    0.09
     diff
    0.08
     diffusion
    0.08
     across
    0.08
     spreads
    0.08
    Activations Density 0.024%

    No Known Activations