Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29388
    Prev
    Next
    INDEX
    Explanations

    numeric values and specifications related to speed and distance

    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
    ındır
    -0.07
    luž
    -0.07
    ribly
    -0.07
    ompson
    -0.07
    nty
    -0.07
    olo
    -0.07
    ystone
    -0.06
    ilogy
    -0.06
    erox
    -0.06
    Äħd
    -0.06
    POSITIVE LOGITS
     speeds
    0.20
     speed
    0.19
    speed
    0.18
    -speed
    0.17
     Speed
    0.15
    éĢŁåº¦
    0.15
    Speed
    0.15
    .speed
    0.15
    _speed
    0.14
    (speed
    0.14
    Activations Density 0.191%

    No Known Activations