© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126736
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest giving advice or 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
    isans
    -0.07
    uja
    -0.07
     Fulton
    -0.07
    usto
    -0.07
    oce
    -0.06
    eurs
    -0.06
    nable
    -0.06
    oster
    -0.06
    VISIBLE
    -0.06
    ignet
    -0.06
    POSITIVE LOGITS
    acob
    0.07
    emek
    0.07
    atk
    0.07
    .epam
    0.06
    iska
    0.06
    FFE
    0.06
     bury
    0.06
     اÙĦÙĤرÙĨ
    0.06
    currentColor
    0.06
    bart
    0.06
    Activations Density 0.011%

    No Known Activations