© 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. 15-LLAMASCOPE-RES-131K
    11. 103590
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the action of rolling or related movements

    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
    posable
    -0.07
    liers
    -0.07
    istory
    -0.07
    >tag
    -0.07
    .outer
    -0.07
    ">ÃĹ</
    -0.07
    ĥ½
    -0.07
    .jd
    -0.07
     éķ
    -0.07
    bris
    -0.07
    POSITIVE LOGITS
     rolling
    0.15
     roll
    0.14
     Roll
    0.14
    rolling
    0.13
    .Roll
    0.13
     Rolling
    0.13
     rolls
    0.13
    Roll
    0.13
    -roll
    0.12
     rolled
    0.12
    Activations Density 0.031%

    No Known Activations