© 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. 62460
    Prev
    Next
    INDEX
    Explanations

    terms related to knowledge, reading, and support

    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
    perse
    -0.06
    ounge
    -0.06
    iage
    -0.06
     tamp
    -0.06
    avou
    -0.06
     sequencing
    -0.06
     cô
    -0.06
    /md
    -0.06
     responseObject
    -0.06
    indr
    -0.06
    POSITIVE LOGITS
     anymore
    0.09
     need
    0.08
    oupon
    0.07
     permission
    0.07
    need
    0.07
    ussen
    0.07
     NEED
    0.07
     Boyd
    0.07
    849
    0.06
    pton
    0.06
    Activations Density 0.022%

    No Known Activations