© 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. 27943
    Prev
    Next
    INDEX
    Explanations

    titles of academic journals and publications related to gynecological research

    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
     Duis
    -0.07
    ipur
    -0.07
    okus
    -0.07
    éĤ¦
    -0.07
    izu
    -0.07
    æ´ĭ
    -0.07
    LTR
    -0.07
    IRROR
    -0.07
     Erotik
    -0.07
    pais
    -0.07
    POSITIVE LOGITS
     Camb
    0.06
     Conc
    0.05
     Mol
    0.05
    amel
    0.05
     Powder
    0.05
    imid
    0.05
    ers
    0.05
     balances
    0.05
     Fat
    0.05
     lump
    0.05
    Activations Density 0.005%

    No Known Activations