© 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. 15000
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to functions or variables

    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
    tor
    -0.07
    rol
    -0.06
    iti
    -0.06
    ute
    -0.06
     Hal
    -0.06
    hal
    -0.06
    tim
    -0.06
    ea
    -0.05
    mann
    -0.05
    ÑĥÑĢн
    -0.05
    POSITIVE LOGITS
    ftware
    0.11
    bsite
    0.11
    apons
    0.10
    egral
    0.09
    cluding
    0.09
    autiful
    0.09
    adays
    0.09
    cluded
    0.09
    ctrine
    0.08
    bsites
    0.08
    Activations Density 0.144%

    No Known Activations