© 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. 59976
    Prev
    Next
    INDEX
    Explanations

    various forms of verbal and adjectival word endings

    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
     addCriterion
    -0.08
     kraje
    -0.08
    podob
    -0.08
    $MESS
    -0.08
     skoro
    -0.07
    رØŃ
    -0.07
    INVAL
    -0.07
    bsolute
    -0.07
     PureComponent
    -0.07
    æ°
    -0.07
    POSITIVE LOGITS
    âĦ¢
    0.10
    ®
    0.08
     âĦ
    0.07
    tm
    0.07
    TM
    0.07
     sorts
    0.07
    ÂĻ
    0.06
     kin
    0.06
     cy
    0.06
    ypse
    0.06
    Activations Density 0.056%

    No Known Activations