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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-LLAMASCOPE-RES-131K
    6. 5421
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax or keywords

    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
    égor
    -0.08
    TW
    -0.07
    orra
    -0.07
    pmat
    -0.07
    oldem
    -0.07
    ypse
    -0.07
    lege
    -0.07
    ifest
    -0.07
    _FOREACH
    -0.07
    atism
    -0.07
    POSITIVE LOGITS
     Builder
    0.07
     jspb
    0.07
     com
    0.06
    침
    0.06
    Lite
    0.06
     ByteString
    0.06
    wire
    0.06
     gaz
    0.06
    Builder
    0.06
     Lip
    0.06
    Activations Density 0.001%

    No Known Activations