© 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. 61270
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of certain items or features, often highlighted with the word "some."

    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
    etur
    -0.07
    emean
    -0.07
    amientos
    -0.06
    groupon
    -0.06
    øre
    -0.06
    getic
    -0.06
     ÐŀÑģÑĤ
    -0.06
     setDescription
    -0.06
    à¸Ļวà¸Ļ
    -0.06
    arked
    -0.06
    POSITIVE LOGITS
     examples
    0.14
     example
    0.12
     Examples
    0.10
     highlights
    0.10
    examples
    0.10
    Examples
    0.09
     exemp
    0.09
     notable
    0.09
     Example
    0.08
     names
    0.08
    Activations Density 0.013%

    No Known Activations