© 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. 120756
    Prev
    Next
    INDEX
    Explanations

    numerical data and mathematical 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
    iet
    -0.06
     Networks
    -0.06
    layer
    -0.06
    uf
    -0.06
    çĴ°
    -0.06
    ิย
    -0.06
    ossil
    -0.06
    aes
    -0.06
     Guerr
    -0.06
    ush
    -0.05
    POSITIVE LOGITS
    placements
    0.07
    QUIRES
    0.06
    éli
    0.06
    Å¡ti
    0.06
    RAP
    0.06
     bul
    0.06
    plx
    0.06
    -basket
    0.06
    ãĥ¼ãĥŃ
    0.06
     vess
    0.06
    Activations Density 0.011%

    No Known Activations