© 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. 61172
    Prev
    Next
    INDEX
    Explanations

    references to existing systems and technologies within various contexts

    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
    åľ¨çº¿è§Ĥçľĭ
    -0.07
    .appspot
    -0.07
     erken
    -0.07
    kir
    -0.07
    ÐIJÑĢÑħÑĸв
    -0.06
    enso
    -0.06
    amba
    -0.06
    vou
    -0.06
    _principal
    -0.06
     živ
    -0.06
    POSITIVE LOGITS
     already
    0.20
    already
    0.18
     existing
    0.17
     Already
    0.17
    Already
    0.16
     Existing
    0.14
     bereits
    0.13
    existing
    0.13
    Existing
    0.12
    å·²ç»ı
    0.12
    Activations Density 0.125%

    No Known Activations