© 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. 95155
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating levels of intensity or difficulty

    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
    erate
    -0.07
     olm
    -0.06
    Disposition
    -0.06
    aoke
    -0.06
    arest
    -0.06
    }elseif
    -0.06
     )↵↵↵↵↵↵↵↵
    -0.06
    ignon
    -0.06
    addock
    -0.06
    mond
    -0.06
    POSITIVE LOGITS
     ever
    0.14
     previous
    0.10
    ever
    0.09
    -ever
    0.09
    previous
    0.09
     EVER
    0.09
     yesterday
    0.08
     jamais
    0.08
     previously
    0.08
    .previous
    0.07
    Activations Density 0.011%

    No Known Activations