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. 5401
    Prev
    Next
    INDEX
    Explanations

    phrases indicating methods or approaches

    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
    ieri
    -0.07
    arts
    -0.06
    ientos
    -0.06
    oss
    -0.06
    Ø·ÙĦ
    -0.06
    pector
    -0.06
    achi
    -0.06
    CAF
    -0.06
    lech
    -0.06
    iges
    -0.06
    POSITIVE LOGITS
     way
    0.12
     WAY
    0.07
    .way
    0.07
     of
    0.07
    eway
    0.07
    thur
    0.06
    odus
    0.06
    .getOwnProperty
    0.06
     Way
    0.06
     Bid
    0.06
    Activations Density 0.008%

    No Known Activations