© 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. 129078
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the provision of information or resources for planning and travel

    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
     morale
    -0.07
    pta
    -0.06
    mour
    -0.06
    enga
    -0.06
     Geile
    -0.06
     ours
    -0.06
    ects
    -0.06
    ÌĨ
    -0.06
    mund
    -0.06
    owns
    -0.06
    POSITIVE LOGITS
    \CMS
    0.08
    quam
    0.06
     gal
    0.06
     Fel
    0.06
     Andrews
    0.06
     gall
    0.06
    %č↵
    0.06
    aso
    0.06
    889
    0.06
    /gtest
    0.06
    Activations Density 0.001%

    No Known Activations