© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82474
    Prev
    Next
    INDEX
    Explanations

    terms related to developers and programming roles

    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
    ameda
    -0.07
    AllowAnonymous
    -0.07
    gre
    -0.07
    vä
    -0.07
    ale
    -0.07
    lesen
    -0.07
    velte
    -0.07
    uate
    -0.07
    istas
    -0.06
    urate
    -0.06
    POSITIVE LOGITS
    ship
    0.08
    /design
    0.07
    ê²
    0.07
    ial
    0.07
    preneur
    0.07
    stvo
    0.06
    /engine
    0.06
    /compiler
    0.06
    ÑĢеменно
    0.06
    ially
    0.06
    Activations Density 0.005%

    No Known Activations