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. 9-LLAMASCOPE-RES-131K
    6. 96049
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to files or paths

    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
    ible
    -0.06
    AndWait
    -0.06
    aq
    -0.05
    udi
    -0.05
     Sür
    -0.05
    agan
    -0.05
    oure
    -0.05
     tl
    -0.05
     ourselves
    -0.05
     supply
    -0.05
    POSITIVE LOGITS
     automáticamente
    0.07
    енз
    0.07
    #ad
    0.07
    ëĭī
    0.07
     automát
    0.07
    \Bridge
    0.07
    è¼
    0.07
    arness
    0.07
    ushman
    0.07
     tô
    0.07
    Activations Density 0.000%

    No Known Activations