© 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. 30620
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing significant magnitude or extent

    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
    öt
    -0.07
    اراÙĨ
    -0.06
    à¥Ģय
    -0.06
    çĵ¶
    -0.06
    kind
    -0.06
    sse
    -0.06
     Nice
    -0.06
    éĥİ
    -0.06
    æ®Ĭ
    -0.06
    EFAULT
    -0.06
    POSITIVE LOGITS
    ly
    0.09
     amount
    0.08
    íŀĪ
    0.08
     force
    0.08
    LY
    0.07
    çĦ¶
    0.07
    essaging
    0.07
     ÑĦакÑĤ
    0.07
     magnitude
    0.07
    usalem
    0.07
    Activations Density 0.003%

    No Known Activations