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. 44281
    Prev
    Next
    INDEX
    Explanations

    Java import statements from Apache libraries

    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
     miêu
    -0.07
     lapse
    -0.06
     interior
    -0.05
     landed
    -0.05
    inline
    -0.05
     malignant
    -0.05
    िद
    -0.05
    /list
    -0.05
    .location
    -0.05
    nap
    -0.05
    POSITIVE LOGITS
     org
    0.08
     springfox
    0.07
     sun
    0.07
     redis
    0.07
     spoon
    0.06
     seedu
    0.06
     scal
    0.06
     reactor
    0.06
     pl
    0.06
     ru
    0.06
    Activations Density 0.003%

    No Known Activations