© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 57706
    Prev
    Next
    INDEX
    Explanations

    file formats and types of documents available for download

    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
    Å¡ek
    -0.09
    leck
    -0.07
    stÅĻed
    -0.07
    GRAM
    -0.07
    овеÑĢ
    -0.07
    agenta
    -0.07
    ìĹĦ
    -0.07
    lessly
    -0.07
    vinc
    -0.06
    ONTAL
    -0.06
    POSITIVE LOGITS
     format
    0.09
     formats
    0.07
    idlo
    0.07
    å½¢å¼ı
    0.07
     formato
    0.07
    reno
    0.07
     Dün
    0.06
    åĶ¯
    0.06
    æł¼å¼ı
    0.06
     Bent
    0.06
    Activations Density 0.002%

    No Known Activations