© 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. 120630
    Prev
    Next
    INDEX
    Explanations

    references to specific brands or products

    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
    asia
    -0.07
    edral
    -0.07
    redients
    -0.06
    AndPassword
    -0.06
    redient
    -0.06
    utherford
    -0.06
    mploy
    -0.06
    ãĥªãĥ¼
    -0.06
     Unity
    -0.06
    ler
    -0.06
    POSITIVE LOGITS
    inizi
    0.07
    trag
    0.07
    ̣
    0.07
    bero
    0.06
    attern
    0.06
    ayi
    0.06
    cano
    0.06
    enco
    0.06
    jez
    0.06
    eil
    0.06
    Activations Density 0.000%

    No Known Activations