© 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. 87108
    Prev
    Next
    INDEX
    Explanations

    questions related to advice and guidance

    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
    olle
    -0.07
    ól
    -0.07
    argent
    -0.07
    isia
    -0.07
    sei
    -0.06
    weis
    -0.06
    sie
    -0.06
     Pru
    -0.06
    uzu
    -0.06
    artment
    -0.06
    POSITIVE LOGITS
     advice
    0.06
     Advice
    0.06
    ikon
    0.06
    .LookAndFeel
    0.06
    ãĤ¦ãĥĪ
    0.06
    вÑĸÑĤ
    0.06
    ormsg
    0.06
    .scalablytyped
    0.06
    à¥ī
    0.06
     discipline
    0.06
    Activations Density 0.011%

    No Known Activations