Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96209
    Prev
    Next
    INDEX
    Explanations

    technical terms and file extensions related to programming and server outputs

    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
    éļĨ
    -0.08
     dilig
    -0.08
    æº
    -0.07
    ivec
    -0.07
    SPORT
    -0.07
    .createFrom
    -0.07
    ãİ
    -0.07
    .freeze
    -0.07
    евиÑĩ
    -0.07
    ỳ
    -0.07
    POSITIVE LOGITS
     Georges
    0.06
    achts
    0.06
     McKay
    0.06
    ware
    0.06
    ichten
    0.06
     Cooke
    0.05
    Unnamed
    0.05
    Mapper
    0.05
    tract
    0.05
    ower
    0.05
    Activations Density 0.004%

    No Known Activations