© 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. 40171
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental impact and transportation

    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
    æĭĶ
    -0.07
     åĬ
    -0.07
     rov
    -0.07
     drains
    -0.06
    ONO
    -0.06
    ãĥĨãĥ«
    -0.06
    .Function
    -0.06
    vod
    -0.06
     Antar
    -0.06
    kart
    -0.06
    POSITIVE LOGITS
     safety
    0.11
     Safety
    0.10
    Safety
    0.09
    afety
    0.09
     haz
    0.07
     hazardous
    0.07
     Safe
    0.07
     safe
    0.07
     safer
    0.07
     Lac
    0.07
    Activations Density 0.003%

    No Known Activations