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. 5565
    Prev
    Next
    INDEX
    Explanations

    structured elements or cases within code logic

    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
    arry
    -0.07
    oyo
    -0.06
     nowhere
    -0.06
    egend
    -0.06
    essen
    -0.06
    orate
    -0.06
    644
    -0.05
    ench
    -0.05
     Ain
    -0.05
    donnees
    -0.05
    POSITIVE LOGITS
    :↵
    0.18
    :↵↵
    0.14
    :č↵
    0.14
    :↵↵↵
    0.14
    ():↵
    0.13
     :↵
    0.13
    ":↵
    0.12
    ï¼ļ↵
    0.12
    :{↵
    0.11
    ':↵
    0.11
    Activations Density 0.025%

    No Known Activations