© 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 EvalsExportsAPI 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. 106516
    Prev
    Next
    INDEX
    Explanations

    elements and structures related to mathematical or logical expressions

    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
    åı«
    -0.06
    -packages
    -0.06
    alleng
    -0.06
    front
    -0.06
    itter
    -0.06
    /values
    -0.06
     Crowley
    -0.06
    ewire
    -0.06
    @Web
    -0.06
    ิศ
    -0.06
    POSITIVE LOGITS
    ÃŃk
    0.08
     such
    0.07
    anes
    0.07
     concept
    0.07
    iki
    0.07
    ìn
    0.07
     Such
    0.06
    è¿Ļç§į
    0.06
    etu
    0.06
    atore
    0.06
    Activations Density 0.104%

    No Known Activations