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. 22-LLAMASCOPE-RES-131K
    6. 5617
    Prev
    Next
    INDEX
    Explanations

    various heading levels and formatting indicators in a document

    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
    uality
    -0.08
     nhau
    -0.08
     behalf
    -0.07
    ritable
    -0.07
    sert
    -0.07
    Äįet
    -0.07
    skyt
    -0.07
     násled
    -0.07
    ../../
    -0.07
    à¹Ĥ
    -0.07
    POSITIVE LOGITS
    oret
    0.10
    #↵↵
    0.10
    ##↵↵
    0.09
    ###↵↵
    0.09
    oretical
    0.07
    maal
    0.07
    aft
    0.06
    ispens
    0.06
    #č↵
    0.06
    orent
    0.06
    Activations Density 0.006%

    No Known Activations