© 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. 95444
    Prev
    Next
    INDEX
    Explanations

    keywords related to media or video content

    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
    amu
    -0.07
    ibre
    -0.07
    king
    -0.07
    onz
    -0.07
    ÙĨÚ¯
    -0.07
    ecycle
    -0.07
    lsi
    -0.07
    eworld
    -0.06
    ÛĮدا
    -0.06
    طع
    -0.06
    POSITIVE LOGITS
     Jenner
    0.06
     cit
    0.06
     Pur
    0.06
    .direct
    0.06
     Williamson
    0.06
    377
    0.06
     sol
    0.06
    ople
    0.06
    401
    0.06
     conserv
    0.05
    Activations Density 0.000%

    No Known Activations