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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 76837
    Prev
    Next
    INDEX
    Explanations

    numerical representations of years

    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
     Pear
    -0.07
    ife
    -0.06
    सर
    -0.06
    atz
    -0.06
    еÑģи
    -0.06
     vul
    -0.06
    .alibaba
    -0.06
     jen
    -0.06
    olini
    -0.06
    _ALT
    -0.05
    POSITIVE LOGITS
    oje
    0.09
    lico
    0.08
    ugins
    0.07
    ancel
    0.07
    andest
    0.07
    uitka
    0.07
    utzer
    0.07
    ÑĥÑĢг
    0.07
    chter
    0.07
    ByExample
    0.07
    Activations Density 0.020%

    No Known Activations