© 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. 40336
    Prev
    Next
    INDEX
    Explanations

    references to types of insurance and related services

    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
     and
    -0.06
    elerik
    -0.06
    uding
    -0.06
    essler
    -0.06
    [
    -0.06
     hypothetical
    -0.06
     Brass
    -0.05
    ud
    -0.05
    1
    -0.05
     imaginary
    -0.05
    POSITIVE LOGITS
    Łèĥ½
    0.09
     WHETHER
    0.08
     CLAIM
    0.08
    ê·ł
    0.07
    ï¼Ĵï¼IJ
    0.07
    ylko
    0.07
    kees
    0.07
    VertexArray
    0.07
    _FEATURE
    0.07
    ÙĬتÙĬ
    0.07
    Activations Density 0.020%

    No Known Activations