© 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. 40492
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases about properties and their features

    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
    //{{
    -0.07
    .pretty
    -0.07
    ần
    -0.07
    /people
    -0.07
     nuru
    -0.07
    ãĥ¼ãĥ«ãĥī
    -0.06
    еÑģи
    -0.06
    TTY
    -0.06
    .Dev
    -0.06
    iras
    -0.06
    POSITIVE LOGITS
    querque
    0.07
    indrome
    0.07
    Ñįй
    0.06
    icari
    0.06
    á»ijt
    0.06
    534
    0.06
    cken
    0.06
     STORAGE
    0.06
     shovel
    0.06
    rear
    0.06
    Activations Density 0.028%

    No Known Activations