© 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. 94005
    Prev
    Next
    INDEX
    Explanations

    language that indicates change or comparison

    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
    fp
    -0.06
    326
    -0.06
    kus
    -0.06
    RAR
    -0.06
    LOT
    -0.06
    ÏĦά
    -0.05
    arg
    -0.05
     meg
    -0.05
    ablo
    -0.05
    imer
    -0.05
    POSITIVE LOGITS
     previously
    0.29
     Previously
    0.25
     previous
    0.24
    Previously
    0.23
     Previous
    0.19
    previous
    0.19
    Previous
    0.18
    .previous
    0.17
    (previous
    0.16
    åİŁæĿ¥
    0.16
    Activations Density 0.119%

    No Known Activations