© 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. 119539
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an opinion or evaluation about choices and decisions

    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
     Lair
    -0.07
    enes
    -0.06
    ulaire
    -0.06
    agua
    -0.06
    orz
    -0.06
    PIP
    -0.06
     also
    -0.06
    urr
    -0.06
    ulos
    -0.06
    even
    -0.06
    POSITIVE LOGITS
     merely
    0.11
     simply
    0.10
     simplement
    0.10
    Simply
    0.07
     Simply
    0.07
     اÛĮÙĨÚ©Ùĩ
    0.07
    بس
    0.06
    |required
    0.06
    Å¡ak
    0.06
    .scalablytyped
    0.06
    Activations Density 0.027%

    No Known Activations