© 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. 15-LLAMASCOPE-RES-131K
    6. 61609
    Prev
    Next
    INDEX
    Explanations

    references to handshakes and physical gestures of greeting or agreement

    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
    ummings
    -0.07
    egr
    -0.07
    irsch
    -0.07
    loff
    -0.07
    ighthouse
    -0.07
    FY
    -0.06
    _gift
    -0.06
    :params
    -0.06
    ymes
    -0.06
    azzi
    -0.06
    POSITIVE LOGITS
    /thumb
    0.07
     solidity
    0.07
    linger
    0.06
    álo
    0.06
    æı¡
    0.06
    imm
    0.06
    bidden
    0.06
    -bars
    0.06
    ewidth
    0.06
    auer
    0.06
    Activations Density 0.007%

    No Known Activations