© 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. 71758
    Prev
    Next
    INDEX
    Explanations

    negation-related terms

    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
    izu
    -0.07
    dech
    -0.07
    venting
    -0.07
    aturas
    -0.06
    acomment
    -0.06
     ori
    -0.06
    rrha
    -0.06
    emoc
    -0.06
    htag
    -0.06
    uben
    -0.06
    POSITIVE LOGITS
    ients
    0.09
    ANNOT
    0.09
    ifies
    0.08
    iates
    0.08
    istically
    0.07
    cribes
    0.07
    ologically
    0.07
    ght
    0.07
    ise
    0.07
    ically
    0.07
    Activations Density 0.061%

    No Known Activations