© 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. 116777
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating the end of sentences

    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
    Unfortunately
    -0.09
     unfortunately
    -0.09
    Sadly
    -0.08
     Unfortunately
    -0.08
     sadly
    -0.08
     Sadly
    -0.07
     downside
    -0.07
    ocked
    -0.07
     leider
    -0.07
    onus
    -0.07
    POSITIVE LOGITS
     nevertheless
    0.22
    Nevertheless
    0.21
     Nonetheless
    0.20
     Nevertheless
    0.20
     nonetheless
    0.20
    noch
    0.14
     but
    0.14
    etheless
    0.13
     Still
    0.11
    ï¼Įä½Ĩ
    0.11
    Activations Density 0.160%

    No Known Activations