© 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. 83235
    Prev
    Next
    INDEX
    Explanations

    legislative terminology and rankings in competitive settings

    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
    !..
    -0.07
    .)↵↵↵↵
    -0.07
    ritten
    -0.06
    ÙĶ
    -0.06
    kı
    -0.06
    hoff
    -0.06
    ̣
    -0.06
    /cop
    -0.06
    olation
    -0.06
    .Mask
    -0.06
    POSITIVE LOGITS
     didSet
    0.06
    _customize
    0.06
    497
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    .EventArgs
    0.06
    åIJ
    0.06
    _firstname
    0.06
    oreferrer
    0.06
    ekyll
    0.06
    (([
    0.06
    Activations Density 0.025%

    No Known Activations