© 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. 128489
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinions and emotional responses toward art and entertainment

    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
    Å
    -0.07
    ogui
    -0.07
    isy
    -0.06
     anarchist
    -0.06
    osu
    -0.06
     black
    -0.06
    à¹Ĥà¸Ķ
    -0.06
    NL
    -0.06
    .scalablytyped
    -0.06
     geek
    -0.06
    POSITIVE LOGITS
     worst
    0.07
     Zub
    0.07
    pseudo
    0.07
    Attempt
    0.07
     worse
    0.07
     faker
    0.07
     artificial
    0.07
    Å¡ka
    0.06
    åķĨ
    0.06
     amat
    0.06
    Activations Density 0.046%

    No Known Activations