© 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. 55846
    Prev
    Next
    INDEX
    Explanations

    references to turning devices on or off

    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
    icious
    -0.07
    qli
    -0.07
     Dün
    -0.07
    intr
    -0.07
    à¥Ģण
    -0.07
    dsp
    -0.07
    raj
    -0.07
    icz
    -0.07
    ains
    -0.07
    cona
    -0.06
    POSITIVE LOGITS
    SKU
    0.07
    TEGR
    0.07
    /off
    0.07
     cro
    0.06
     Jas
    0.06
    hung
    0.06
    /react
    0.06
    :animated
    0.06
    OFF
    0.06
    ÑĢак
    0.06
    Activations Density 0.016%

    No Known Activations