Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43402
    Prev
    Next
    INDEX
    Explanations

    instances of code related to image data manipulation and selection

    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
     ÐĶоб
    -0.04
    estone
    -0.04
     STDCALL
    -0.04
    -pills
    -0.04
     Desert
    -0.04
     Dil
    -0.04
    ùi
    -0.04
    arrison
    -0.04
    clipse
    -0.04
    utow
    -0.04
    POSITIVE LOGITS
     data
    0.54
    data
    0.46
    -data
    0.42
    .data
    0.41
    (data
    0.40
     Data
    0.39
     DATA
    0.39
    _data
    0.38
    =data
    0.38
    	data
    0.37
    Activations Density 0.158%

    No Known Activations