© 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. 3761
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experience and excitement related to summer activities

    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
    obus
    -0.07
    ElementsBy
    -0.07
    Accessory
    -0.06
    ãģĩ
    -0.06
    EMPLATE
    -0.06
     Federal
    -0.06
    INET
    -0.06
    _accessible
    -0.06
    aida
    -0.06
    igel
    -0.06
    POSITIVE LOGITS
     placements
    0.07
     placement
    0.07
     durations
    0.07
    angs
    0.06
     host
    0.06
     duration
    0.06
    ieber
    0.06
    eren
    0.06
    departure
    0.06
    -duration
    0.06
    Activations Density 0.001%

    No Known Activations