Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 29038
    Prev
    Next
    INDEX
    Explanations

    words related to theme park attractions and experiences

    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
    \grid
    -0.07
    647
    -0.06
    564
    -0.06
     fancy
    -0.06
     madness
    -0.06
    nun
    -0.06
     TypeName
    -0.06
    [url
    -0.06
    .Messages
    -0.06
     otherwise
    -0.06
    POSITIVE LOGITS
     tieten
    0.07
     modne
    0.07
    nek
    0.06
     takson
    0.06
    eda
    0.06
    ags
    0.06
     ncols
    0.06
     SCALE
    0.06
    vatel
    0.06
    ela
    0.06
    Activations Density 0.000%

    No Known Activations