© 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 EvalsExportsinterp-engineNEWAPI 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. 38881
    Prev
    Next
    INDEX
    Explanations

    elements related to science fiction literature and its context

    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
     Verfüg
    -0.07
     guten
    -0.06
    ennie
    -0.06
    алÑĮнÑĥ
    -0.06
    ustos
    -0.06
     Kosten
    -0.06
    aq
    -0.06
     kür
    -0.06
    utility
    -0.06
     Medicare
    -0.06
    POSITIVE LOGITS
    è¾°
    0.07
    inz
    0.07
    471
    0.07
    457
    0.07
    ÃŁ
    0.07
     âĢŀ
    0.07
    âŁ
    0.07
    ä
    0.07
     resp
    0.07
    Beans
    0.07
    Activations Density 0.321%

    No Known Activations