© 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. 40695
    Prev
    Next
    INDEX
    Explanations

    information about genetic screening services and testing

    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
    zem
    -0.07
    utt
    -0.06
    zilla
    -0.06
    izo
    -0.06
    .trailing
    -0.06
    .SelectedItems
    -0.06
    earer
    -0.06
    unga
    -0.06
    ume
    -0.06
    POSITIVE LOGITS
    ané
    0.07
    alytics
    0.07
    needle
    0.07
    egis
    0.06
    alth
    0.06
    URN
    0.06
    -results
    0.06
    _results
    0.06
     Test
    0.06
     test
    0.06
    Activations Density 0.002%

    No Known Activations