© 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. 9-LLAMASCOPE-RES-131K
    11. 97636
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the significance of concepts or actions

    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
    iers
    -0.07
    abus
    -0.07
    igu
    -0.06
     Sexe
    -0.06
    etry
    -0.06
    izi
    -0.06
    zia
    -0.06
    ylie
    -0.06
    ÑģÑĤва
    -0.06
    achten
    -0.06
    POSITIVE LOGITS
    FUL
    0.08
    full
    0.07
    itzer
    0.07
    esan
    0.07
     ere
    0.07
    creens
    0.07
    ful
    0.06
     importance
    0.06
    eous
    0.06
     Importance
    0.06
    Activations Density 0.015%

    No Known Activations