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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119213
    Prev
    Next
    INDEX
    Explanations

    references to the passage of time measured in months

    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
    em
    -0.07
    ourg
    -0.06
    ging
    -0.06
    evi
    -0.06
    ability
    -0.06
    throp
    -0.06
    IMS
    -0.06
    punk
    -0.06
    oh
    -0.06
    oes
    -0.05
    POSITIVE LOGITS
    -long
    0.14
     ago
    0.12
    份
    0.10
    -old
    0.09
    long
    0.09
    /year
    0.09
     Ago
    0.08
     ÙħÛĮÙĦادÛĮ
    0.08
    -plus
    0.08
    ago
    0.08
    Activations Density 0.017%

    No Known Activations