© 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. 31293
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tags in the text

    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
    mbH
    -0.07
    izr
    -0.07
    USTER
    -0.06
    udad
    -0.06
    uster
    -0.06
    bÃŃr
    -0.06
    ledon
    -0.06
    edl
    -0.06
    coni
    -0.06
     пÑĢеÑģ
    -0.06
    POSITIVE LOGITS
     title
    0.09
     titled
    0.08
    title
    0.07
    -title
    0.07
    ward
    0.07
    -heading
    0.06
    称
    0.06
    TITLE
    0.06
     entitled
    0.06
    DialogTitle
    0.06
    Activations Density 0.003%

    No Known Activations