© 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. 61195
    Prev
    Next
    INDEX
    Explanations

    procedural instructions related to plant care or food preparation

    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
    reur
    -0.06
    ppy
    -0.06
    rž
    -0.06
    atz
    -0.06
    asl
    -0.06
    mür
    -0.06
    æĬľ
    -0.06
    obs
    -0.06
    ãĥ¼ãĥ©
    -0.06
    åĭŁ
    -0.06
    POSITIVE LOGITS
     sometimes
    0.08
     usually
    0.07
    sometimes
    0.07
    usually
    0.07
    åħĭæĸ¯
    0.07
    onec
    0.07
    angan
    0.07
    ometimes
    0.06
     either
    0.06
     też
    0.06
    Activations Density 0.016%

    No Known Activations