© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 73287
    Prev
    Next
    INDEX
    Explanations

    references to genetic testing and screening programs

    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
    INLINE
    -0.10
    ptrdiff
    -0.09
    eyse
    -0.09
    вÑĸлÑĮ
    -0.09
    /legal
    -0.08
    aç
    -0.08
    Wildcard
    -0.08
    ãĤ¤ãĥ³ãĥĪ
    -0.08
    ëłĮ
    -0.08
    ismet
    -0.08
    POSITIVE LOGITS
    Ìģ
    0.08
    ix
    0.06
    ay
    0.06
    ited
    0.06
    oo
    0.06
    .com
    0.06
    âĢ¦↵
    0.06
    co
    0.05
    -s
    0.05
    bers
    0.05
    Activations Density 0.174%

    No Known Activations