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. 31-LLAMASCOPE-RES-131K
    6. 43817
    Prev
    Next
    INDEX
    Explanations

    references to time and temporal concepts

    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
    ooter
    -0.07
    .scalablytyped
    -0.07
    .MixedReality
    -0.06
    anova
    -0.06
    arel
    -0.06
    stants
    -0.06
     CascadeType
    -0.06
    oe
    -0.06
    idas
    -0.06
    ibe
    -0.06
    POSITIVE LOGITS
     when
    0.16
     of
    0.11
    when
    0.10
     where
    0.10
     characterized
    0.09
     WHEN
    0.09
     когда
    0.09
     marked
    0.08
     quando
    0.08
     kdy
    0.08
    Activations Density 0.010%

    No Known Activations