© 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. 87344
    Prev
    Next
    INDEX
    Explanations

    phrases related to traffic incidents and road safety

    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
    uzz
    -0.07
    ael
    -0.06
    _UTF
    -0.06
    oren
    -0.06
    acer
    -0.06
    bler
    -0.06
    辺
    -0.06
    chai
    -0.06
    ACHER
    -0.06
     actionTypes
    -0.06
    POSITIVE LOGITS
    coming
    0.10
    Coming
    0.08
     Coming
    0.08
     coming
    0.08
    istring
    0.08
     incoming
    0.07
    DownList
    0.07
     opposite
    0.07
     passing
    0.06
    Direction
    0.06
    Activations Density 0.048%

    No Known Activations