© 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. 73273
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating negation or exceptions

    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
    astes
    -0.07
    anki
    -0.06
    uster
    -0.06
    obl
    -0.06
    ulet
    -0.06
    ourg
    -0.06
    DataService
    -0.06
     vibrator
    -0.06
    fsp
    -0.06
    aste
    -0.06
    POSITIVE LOGITS
     Article
    0.07
     GOODMAN
    0.07
    OTH
    0.07
     Goodman
    0.07
     ARTICLE
    0.07
    -article
    0.07
    mts
    0.07
     article
    0.07
    Advertisements
    0.07
    itten
    0.07
    Activations Density 0.002%

    No Known Activations