© 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. 92736
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and units of measurement

    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
    assin
    -0.06
     enf
    -0.06
    ãĥ¼ãģ®
    -0.06
    arel
    -0.06
     dane
    -0.06
     Sent
    -0.06
    ìĿ¸ìĿĺ
    -0.06
    _SUS
    -0.05
    oman
    -0.05
    _COD
    -0.05
    POSITIVE LOGITS
     cins
    0.10
    -scale
    0.08
    scale
    0.07
    nat
    0.07
    ahoma
    0.06
    å·¦åı³
    0.06
    æķ°
    0.06
    наÑĤ
    0.06
     scale
    0.06
    itelist
    0.06
    Activations Density 0.059%

    No Known Activations