© 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. 94415
    Prev
    Next
    INDEX
    Explanations

    possessive forms related to governance or authority

    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
     kimse
    -0.09
    itler
    -0.07
    kate
    -0.07
     company
    -0.07
    ulle
    -0.06
     compagn
    -0.06
    anken
    -0.06
     personally
    -0.06
     Walt
    -0.06
    aight
    -0.06
    POSITIVE LOGITS
    TestCategory
    0.06
    NetMessage
    0.06
     view
    0.06
     recent
    0.06
    mazon
    0.06
     handling
    0.06
    esch
    0.06
    entes
    0.06
    ãĥ¥
    0.06
    LOPT
    0.06
    Activations Density 0.030%

    No Known Activations