© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 106128
    Prev
    Next
    INDEX
    Explanations

    phrases that involve numerical values or quantities

    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
    erken
    -0.08
    .strings
    -0.08
    äter
    -0.08
    ulan
    -0.08
    iven
    -0.07
     INCIDENTAL
    -0.07
    istrat
    -0.07
    allet
    -0.07
    ãĢģ
    -0.07
    alten
    -0.07
    POSITIVE LOGITS
     resulted
    0.13
     eventually
    0.12
     resulting
    0.10
     then
    0.10
     result
    0.10
     Eventually
    0.10
     Result
    0.10
    Eventually
    0.10
    äºİæĺ¯
    0.09
     finally
    0.09
    Activations Density 0.063%

    No Known Activations