© 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. 55887
    Prev
    Next
    INDEX
    Explanations

    expressions of hope and aspiration related to success or achievement

    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
    /catalog
    -0.08
    κά
    -0.07
    WARE
    -0.06
     Trit
    -0.06
    κοÏħ
    -0.06
    .utility
    -0.06
    utch
    -0.06
     chua
    -0.06
    ÑģÑĤи
    -0.06
     Lesser
    -0.06
    POSITIVE LOGITS
     hopes
    0.08
    ãģķãĤī
    0.07
    igon
    0.06
    boost
    0.06
    ango
    0.06
    ogo
    0.06
    rive
    0.06
    zel
    0.06
    iver
    0.06
     dashed
    0.06
    Activations Density 0.010%

    No Known Activations