© 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 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. 56107
    Prev
    Next
    INDEX
    Explanations

    instances of the prefix "un," 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
    	Copyright
    -0.08
    /***/
    -0.08
     QUI
    -0.08
    herits
    -0.07
    employed
    -0.07
    fillType
    -0.07
    lexport
    -0.07
    /INFO
    -0.07
    .hwp
    -0.07
    alm
    -0.07
    POSITIVE LOGITS
    sc
    0.08
    uer
    0.07
    wis
    0.06
    -
    0.06
    wen
    0.06
     official
    0.06
    pa
    0.06
    nt
    0.06
    /un
    0.06
     tud
    0.06
    Activations Density 0.025%

    No Known Activations