© 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. 56383
    Prev
    Next
    INDEX
    Explanations

    references to specific times or seasons related to holidays and travel

    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
    issen
    -0.07
    imbus
    -0.06
    NB
    -0.06
     XY
    -0.05
    arer
    -0.05
    ador
    -0.05
    _VENDOR
    -0.05
     Sidd
    -0.05
    eten
    -0.05
    rail
    -0.05
    POSITIVE LOGITS
     period
    0.07
    TAIL
    0.07
     ideal
    0.06
     Ideal
    0.06
    intros
    0.06
     busiest
    0.06
     åı
    0.06
     prime
    0.06
    ĮĢ
    0.06
    antz
    0.06
    Activations Density 0.018%

    No Known Activations