© 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. 31048
    Prev
    Next
    INDEX
    Explanations

    references to figures and examples in a structured context

    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
    以ä¸ĭ
    -0.07
    ä¸ĭ
    -0.07
     Below
    -0.06
     ä¸ĭ
    -0.06
    com
    -0.06
    ica
    -0.06
     following
    -0.06
     downstairs
    -0.06
    oni
    -0.06
    umber
    -0.06
    POSITIVE LOGITS
     above
    0.27
    above
    0.23
     Above
    0.23
    Above
    0.22
     ABOVE
    0.21
     вÑĭÑĪе
    0.17
     výše
    0.16
    bove
    0.16
    以ä¸Ĭ
    0.16
    _above
    0.16
    Activations Density 0.040%

    No Known Activations