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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 119711
    Prev
    Next
    INDEX
    Explanations

    themes of emotional expression and introspection in music

    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
    lish
    -0.07
     ngu
    -0.06
     Sing
    -0.06
    çľī
    -0.06
     sing
    -0.06
    doll
    -0.06
    uiltin
    -0.06
     Jug
    -0.06
    çĭ
    -0.06
     jur
    -0.06
    POSITIVE LOGITS
    ulos
    0.08
    akis
    0.07
    apan
    0.07
    esz
    0.07
    onal
    0.07
    íĮ
    0.07
    inos
    0.07
    æĻ¯
    0.07
    .nano
    0.07
    cape
    0.07
    Activations Density 0.021%

    No Known Activations