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. 44050
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and sentence endings

    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
     PLEASE
    -0.08
    PLEASE
    -0.07
     please
    -0.07
    WARNING
    -0.07
     Writes
    -0.07
     Ah
    -0.06
     WARNING
    -0.06
     Appears
    -0.06
    Oops
    -0.06
     Ain
    -0.06
    POSITIVE LOGITS
     We
    0.10
    We
    0.10
     we
    0.10
     Our
    0.09
     really
    0.09
    Our
    0.09
    we
    0.08
     somebody
    0.08
     our
    0.08
     part
    0.07
    Activations Density 0.069%

    No Known Activations