© 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. 78144
    Prev
    Next
    INDEX
    Explanations

    groups and comparisons in clinical study data

    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
    relude
    -0.08
     stdClass
    -0.06
    ROID
    -0.06
    oder
    -0.06
    ords
    -0.06
    _UNICODE
    -0.06
    warm
    -0.06
     Standing
    -0.06
    BASH
    -0.06
     é»
    -0.06
    POSITIVE LOGITS
     group
    0.08
     arm
    0.07
    igroup
    0.07
    è£ķ
    0.07
    (groups
    0.07
    group
    0.06
    antaged
    0.06
     study
    0.06
    _tooltip
    0.06
    494
    0.06
    Activations Density 0.023%

    No Known Activations