© 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. 117643
    Prev
    Next
    INDEX
    Explanations

    references to significant ideas or principles

    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
    assi
    -0.07
    enal
    -0.07
    ahl
    -0.07
    ifen
    -0.07
    .GridView
    -0.07
    unca
    -0.06
    ahlen
    -0.06
    encer
    -0.06
    ÙħاÙĨÛĮ
    -0.06
    ipeg
    -0.06
    POSITIVE LOGITS
     requires
    0.08
     require
    0.07
    plusplus
    0.07
     accomplished
    0.07
     accomplish
    0.06
     difficult
    0.06
     objectives
    0.06
     Sounds
    0.06
     INCLUDE
    0.06
    olean
    0.06
    Activations Density 0.036%

    No Known Activations