© 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. 56029
    Prev
    Next
    INDEX
    Explanations

    parentheses and brackets in code

    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
    asters
    -0.07
     ydk
    -0.07
    anton
    -0.07
    zens
    -0.07
    ì§Ģëħ¸
    -0.07
    cly
    -0.07
    aters
    -0.07
    ãĥªãĥ¼ãĤº
    -0.07
    logue
    -0.07
    <TSource
    -0.07
    POSITIVE LOGITS
    anism
    0.07
    pcf
    0.06
    643
    0.06
     Spieler
    0.06
     çµ
    0.06
     PC
    0.06
    _PC
    0.06
    viso
    0.06
    329
    0.06
    .twitch
    0.06
    Activations Density 0.002%

    No Known Activations