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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 77678
    Prev
    Next
    INDEX
    Explanations

    phrases and elements related to music and entertainment success

    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
    CESS
    -0.07
    .lp
    -0.07
    èIJ
    -0.07
    å
    -0.07
    holm
    -0.07
    å¶
    -0.07
    stagram
    -0.07
    帯
    -0.07
     सà¤ķ
    -0.07
    FieldValue
    -0.07
    POSITIVE LOGITS
     "
    0.06
    ask
    0.06
    0.06
     (
    0.06
    sad
    0.06
     `
    0.06
    ↵
    0.06
     .
    0.06
     cous
    0.06
    Âł
    0.05
    Activations Density 0.011%

    No Known Activations