© 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. 126915
    Prev
    Next
    INDEX
    Explanations

    numerical values and technical specifications related to products or services

    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
    ãģ¾ãģļ
    -0.10
    /Gate
    -0.09
     totiž
    -0.09
     dán
    -0.08
    ERCHANT
    -0.08
    .truth
    -0.08
    زÙĦ
    -0.08
    }elseif
    -0.08
    adge
    -0.08
    (æ°´
    -0.08
    POSITIVE LOGITS
    /or
    0.16
     alike
    0.11
    quot
    0.10
    rogen
    0.09
    amp
    0.08
    rog
    0.08
    phans
    0.07
    AMP
    0.07
    /OR
    0.07
    orra
    0.06
    Activations Density 0.094%

    No Known Activations