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. 43741
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific logos or branding terms

    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
    ynam
    -0.06
     bic
    -0.06
     Levitra
    -0.06
    -football
    -0.06
    ähr
    -0.06
    OMEM
    -0.06
    emoji
    -0.06
    åĩ½
    -0.06
    orum
    -0.06
    UBE
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.08
     Long
    0.08
     zipcode
    0.07
     Domestic
    0.07
     our
    0.06
     Our
    0.06
     Zip
    0.06
     mont
    0.06
     High
    0.06
     succesfully
    0.06
    Activations Density 0.001%

    No Known Activations