© 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. 27285
    Prev
    Next
    INDEX
    Explanations

    references to actors and their roles in film or television

    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
     iParam
    -0.08
    IDD
    -0.08
    iminal
    -0.08
    .scalablytyped
    -0.07
    letal
    -0.07
    OptionsResolver
    -0.07
    zial
    -0.07
    жно
    -0.07
    :animated
    -0.07
    PEAR
    -0.07
    POSITIVE LOGITS
     Haven
    0.06
     Kir
    0.06
    arts
    0.06
    allet
    0.06
     Pf
    0.05
     Marks
    0.05
     opposite
    0.05
     Half
    0.05
     troublesome
    0.05
     /
    0.05
    Activations Density 0.011%

    No Known Activations