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. 44384
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols commonly used in mathematical expressions

    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
    ’S
    -0.09
    ’s
    -0.08
    ’)
    -0.08
    ”—
    -0.07
    ’il
    -0.07
    ’:
    -0.07
     â̦↵↵
    -0.07
    ’re
    -0.07
    ’am
    -0.07
    aben
    -0.07
    POSITIVE LOGITS
     Nashville
    0.12
     Tennessee
    0.09
     --
    0.08
     AH
    0.08
     Memphis
    0.08
     Chattanooga
    0.08
     TN
    0.07
     apparently
    0.07
     Nash
    0.07
     Knoxville
    0.07
    Activations Density 0.007%

    No Known Activations