© 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. 17-LLAMASCOPE-RES-131K
    6. 15680
    Prev
    Next
    INDEX
    Explanations

    articles and determiners indicating quantity or count

    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
    ably
    -0.08
    owitz
    -0.06
    wik
    -0.06
    dech
    -0.06
    udded
    -0.06
    خص
    -0.06
    linky
    -0.06
    ød
    -0.06
    ux
    -0.06
    ooter
    -0.06
    POSITIVE LOGITS
    ione
    0.09
    -handed
    0.07
    idi
    0.07
    alık
    0.07
    -sided
    0.06
    æĸ°çļĦ
    0.06
    -third
    0.06
    oreach
    0.06
    ìĶ©
    0.06
    arb
    0.06
    Activations Density 0.006%

    No Known Activations