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. 22-LLAMASCOPE-RES-131K
    6. 5296
    Prev
    Next
    INDEX
    Explanations

    references to cruise lines and ships

    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
    åĿĬ
    -0.08
    leme
    -0.08
    ovna
    -0.08
    .ua
    -0.07
    Parms
    -0.07
    âĶIJ
    -0.07
    kup
    -0.07
     zipcode
    -0.07
    scalar
    -0.07
    683
    -0.07
    POSITIVE LOGITS
    forth
    0.07
     Spl
    0.07
    uzzi
    0.07
    rew
    0.06
     Mess
    0.06
     split
    0.06
    lier
    0.06
    isen
    0.06
    imer
    0.06
    *)((
    0.06
    Activations Density 0.006%

    No Known Activations