© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95861
    Prev
    Next
    INDEX
    Explanations

    references to pedestrian-related incidents and 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
    ocop
    -0.07
    пÑĢа
    -0.07
    884
    -0.07
    engin
    -0.07
    vais
    -0.07
    otime
    -0.07
    eus
    -0.07
    meno
    -0.07
    ÏĦÏģο
    -0.07
    obox
    -0.06
    POSITIVE LOGITS
     hol
    0.06
    ritte
    0.06
     Gib
    0.06
    ropic
    0.06
    ehler
    0.06
     rat
    0.06
    uche
    0.06
    اباÙĨ
    0.06
    /watch
    0.05
    ivery
    0.05
    Activations Density 0.002%

    No Known Activations