© 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. 28397
    Prev
    Next
    INDEX
    Explanations

    mentions of "Spider" or "spider" in various contexts

    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
    nown
    -0.08
    inters
    -0.08
    /libs
    -0.07
    vard
    -0.07
    imers
    -0.07
    peare
    -0.07
    addin
    -0.07
    èĬ³
    -0.07
    anas
    -0.06
    ably
    -0.06
    POSITIVE LOGITS
    gram
    0.09
    orama
    0.08
    grams
    0.08
    hton
    0.08
    dex
    0.07
    -like
    0.07
    atrix
    0.06
    ular
    0.06
    andalone
    0.06
    ë§ģ
    0.06
    Activations Density 0.003%

    No Known Activations