© 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. 125963
    Prev
    Next
    INDEX
    Explanations

    instances of surprise or unexpected reactions in narratives

    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
    .Automation
    -0.07
    CTS
    -0.07
    nite
    -0.07
    aliz
    -0.07
    oner
    -0.06
    emento
    -0.06
    TestFixture
    -0.06
    ÑĤÑİ
    -0.06
    mour
    -0.06
     Duffy
    -0.06
    POSITIVE LOGITS
    296
    0.06
    unar
    0.06
    ular
    0.06
     ever
    0.06
    922
    0.06
    513
    0.06
    ascar
    0.06
     Narc
    0.06
     Newsp
    0.06
    706
    0.06
    Activations Density 0.009%

    No Known Activations