© 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. 80048
    Prev
    Next
    INDEX
    Explanations

    HTML elements and associated formatting tags

    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
    олж
    -0.06
    é¢ĺ
    -0.06
    ÑĢоб
    -0.06
    gs
    -0.06
    ureau
    -0.06
    ote
    -0.05
    avan
    -0.05
    quiv
    -0.05
    plib
    -0.05
     tot
    -0.05
    POSITIVE LOGITS
    subpackage
    0.07
    elige
    0.07
    eyh
    0.07
    ç¦
    0.07
    oggler
    0.07
    annis
    0.06
    uell
    0.06
    osti
    0.06
    atta
    0.06
    ovah
    0.06
    Activations Density 0.006%

    No Known Activations