© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 94533
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue or quoted statements

    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
    iston
    -0.10
    ectar
    -0.08
    áp
    -0.07
    arker
    -0.07
    ekt
    -0.07
    conte
    -0.07
    ubu
    -0.07
    plet
    -0.07
    enberg
    -0.06
    Ãłi
    -0.06
    POSITIVE LOGITS
    ÑĢд
    0.07
    MUX
    0.06
    浩
    0.06
    Ðİ
    0.06
     terk
    0.06
    uite
    0.06
     Klan
    0.05
    134
    0.05
    ipse
    0.05
    wart
    0.05
    Activations Density 0.026%

    No Known Activations