© 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. 93486
    Prev
    Next
    INDEX
    Explanations

    functional programming concepts related to list and sequence manipulation

    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
    itor
    -0.06
    -0.06
    [
    -0.05
     neighbor
    -0.05
    alen
    -0.05
    alse
    -0.05
    Alchemy
    -0.05
    iu
    -0.05
    ("
    -0.05
    POSITIVE LOGITS
     =č↵
    0.08
    .nano
    0.08
    .)↵↵↵↵
    0.08
    abis
    0.07
    _Lean
    0.07
    )return
    0.07
    å´İ
    0.07
    بÙĪاسطة
    0.07
     náv
    0.07
    /XMLSchema
    0.07
    Activations Density 0.004%

    No Known Activations