Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-LLAMASCOPE-RES-131K
    6. 96232
    Prev
    Next
    INDEX
    Explanations

    references to numbers and their significance in various contexts

    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
    ider
    -0.06
    ActionCreators
    -0.06
    sian
    -0.06
    oha
    -0.06
    ispers
    -0.06
     Tender
    -0.06
     Mein
    -0.06
    Indented
    -0.06
    enza
    -0.06
    PropertyName
    -0.06
    POSITIVE LOGITS
    ãĤ¤ãĥ³ãĥĪ
    0.07
    INGLE
    0.07
    bero
    0.06
    á»įt
    0.06
    ãĥģãĥ£
    0.06
    ylon
    0.06
    umlu
    0.06
    ford
    0.06
    (sym
    0.06
    æ°ı
    0.06
    Activations Density 0.023%

    No Known Activations