© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57512
    Prev
    Next
    INDEX
    Explanations

    phrases related to travel and speed

    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
    phinx
    -0.08
    ephir
    -0.08
    icode
    -0.07
    tridge
    -0.07
    licative
    -0.07
    amburg
    -0.07
    idelberg
    -0.07
    orgetown
    -0.07
    зм
    -0.07
    ç©
    -0.06
    POSITIVE LOGITS
     steady
    0.07
     speed
    0.07
     Sherman
    0.07
     slower
    0.06
     ass
    0.06
    ass
    0.06
     fastest
    0.06
    allas
    0.06
     faster
    0.06
    .speed
    0.06
    Activations Density 0.002%

    No Known Activations