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. 22-LLAMASCOPE-RES-131K
    6. 5566
    Prev
    Next
    INDEX
    Explanations

    geographical names and terms related to mapping

    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
    éϏ
    -0.09
    WithString
    -0.08
    voje
    -0.08
    ãĥ¬ãĥ¼
    -0.07
    .dsl
    -0.07
    ắng
    -0.07
    ToEnd
    -0.07
    _AG
    -0.07
    RAIN
    -0.07
    лÑıн
    -0.07
    POSITIVE LOGITS
     Holt
    0.06
    lash
    0.06
    955
    0.06
    222
    0.06
    372
    0.05
    alli
    0.05
    784
    0.05
    =''
    0.05
    392
    0.05
    izes
    0.05
    Activations Density 0.008%

    No Known Activations