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. 5777
    Prev
    Next
    INDEX
    Explanations

    occurrences of abbreviations, acronyms, or specific formatting styles common in technical or academic writing

    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
    _blob
    -0.06
    ÑĥÑĢг
    -0.06
    alis
    -0.06
    armac
    -0.06
    reshold
    -0.05
     exact
    -0.05
    berman
    -0.05
     al
    -0.05
    acen
    -0.05
     Beer
    -0.05
    POSITIVE LOGITS
    eking
    0.08
    ioso
    0.08
    iah
    0.07
    redi
    0.07
     Grimm
    0.07
    etten
    0.07
    ENCES
    0.07
    Instantiate
    0.07
    QUIRES
    0.07
     tent
    0.06
    Activations Density 0.004%

    No Known Activations