© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 90730
    Prev
    Next
    INDEX
    Explanations

    image links or references in the document

    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
    orum
    -0.07
    zeit
    -0.07
    ½æķ°
    -0.07
    ntl
    -0.07
    ãĤ·ãĥ£ãĥ«
    -0.06
    ìħľ
    -0.06
    noon
    -0.06
    unning
    -0.06
    bred
    -0.06
    connexion
    -0.06
    POSITIVE LOGITS
    ardon
    0.08
    outu
    0.08
    kest
    0.08
    .twitter
    0.07
     @}
    0.07
    ldr
    0.06
    chyb
    0.06
    etics
    0.06
    ALSE
    0.06
    isters
    0.06
    Activations Density 0.001%

    No Known Activations