© 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. 127166
    Prev
    Next
    INDEX
    Explanations

    references to legal cases or statutes

    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
    bourg
    -0.07
     rough
    -0.06
    ilan
    -0.06
    ans
    -0.06
     levels
    -0.06
     hem
    -0.06
    -M
    -0.05
    ih
    -0.05
    anes
    -0.05
     unto
    -0.05
    POSITIVE LOGITS
    endcode
    0.07
    utow
    0.07
    leftright
    0.07
    ieux
    0.07
    nonnull
    0.07
    andler
    0.07
    rax
    0.07
    à¥Ģà¤Ł
    0.07
    ĶĶ
    0.07
    ecycle
    0.06
    Activations Density 0.019%

    No Known Activations