© 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. 85768
    Prev
    Next
    INDEX
    Explanations

    concepts related to education and language training

    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
    uzz
    -0.06
    loor
    -0.06
    acker
    -0.06
    .cc
    -0.06
    arendra
    -0.06
    æ´ŀ
    -0.06
    quir
    -0.06
    bart
    -0.06
    allet
    -0.06
     AuthService
    -0.06
    POSITIVE LOGITS
    _ANDROID
    0.07
    chwitz
    0.06
    508
    0.06
     Champ
    0.06
    -bed
    0.06
    FormField
    0.06
     Bed
    0.06
    imli
    0.06
    å¥
    0.06
    -suite
    0.06
    Activations Density 0.006%

    No Known Activations