© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 119732
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negation or the absence of something

    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
    ziel
    -0.07
    uien
    -0.07
    umn
    -0.07
    uner
    -0.07
    avana
    -0.07
    abase
    -0.07
    hetto
    -0.07
    sterol
    -0.07
    _SLOT
    -0.07
    stuff
    -0.06
    POSITIVE LOGITS
     mere
    0.07
     match
    0.06
     longer
    0.06
     Buen
    0.06
    xious
    0.06
    chan
    0.06
    isy
    0.06
     matter
    0.06
    Å¡ak
    0.06
    jos
    0.06
    Activations Density 0.016%

    No Known Activations