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. 5288
    Prev
    Next
    INDEX
    Explanations

    terms associated with significant or impactful changes and events

    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
    bos
    -0.08
    erman
    -0.07
    ermann
    -0.07
    çok
    -0.07
    ikel
    -0.07
    bies
    -0.07
     оÑĢганизма
    -0.07
    बल
    -0.07
    iddet
    -0.07
    ส
    -0.07
    POSITIVE LOGITS
    s
    0.16
    ly
    0.14
    mente
    0.11
    al
    0.10
    ity
    0.10
    ALLY
    0.10
    ingly
    0.10
    ally
    0.10
     difference
    0.10
    ively
    0.09
    Activations Density 0.008%

    No Known Activations