© 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. 15261
    Prev
    Next
    INDEX
    Explanations

    terms and phrases indicating negation or non-affirmative attributes

    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
    FRING
    -0.07
    ioms
    -0.07
    stances
    -0.07
    CCCCCC
    -0.07
    است
    -0.07
    AZE
    -0.07
    leon
    -0.07
    IVATE
    -0.07
    ÅĻÃŃd
    -0.07
    forman
    -0.07
    POSITIVE LOGITS
     alike
    0.12
    (er
    0.06
     ê·¸ëłĩ
    0.06
     thereof
    0.06
    stery
    0.06
     Cres
    0.06
    /non
    0.06
    ç¦
    0.06
    soever
    0.06
    OTA
    0.06
    Activations Density 0.009%

    No Known Activations