© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95418
    Prev
    Next
    INDEX
    Explanations

    phrases conveying conditional situations or transitions

    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
    oge
    -0.08
    geois
    -0.07
    ogo
    -0.06
    egen
    -0.06
     Plug
    -0.06
    ucc
    -0.06
    /REC
    -0.06
    gnu
    -0.06
    igo
    -0.06
    illa
    -0.06
    POSITIVE LOGITS
     versa
    0.07
    itals
    0.06
    821
    0.06
    hangi
    0.06
    sse
    0.06
    tain
    0.06
     *)"
    0.06
    ÑĢег
    0.06
    idlo
    0.06
     stacks
    0.06
    Activations Density 0.022%

    No Known Activations