© 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. 15-LLAMASCOPE-RES-131K
    11. 27091
    Prev
    Next
    INDEX
    Explanations

    specific keywords associated with significant events or time periods

    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
    2
    -0.06
     pin
    -0.06
    zew
    -0.06
    lesh
    -0.05
    "
    -0.05
    /
    -0.05
    1
    -0.05
    is
    -0.05
     underlying
    -0.05
     Gibbs
    -0.05
    POSITIVE LOGITS
     Ùħباش
    0.12
    Intialized
    0.08
    EIF
    0.08
    GuidId
    0.08
    oÅĪ
    0.08
    OffsetTable
    0.08
    ysz
    0.08
    EmptyEntries
    0.08
    znik
    0.08
    ãĥ¼ãĥª
    0.08
    Activations Density 0.027%

    No Known Activations