© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71013
    Prev
    Next
    INDEX
    Explanations

    language related to rules and regulations regarding the use of force or medical procedures

    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
    -prepend
    -0.08
    206
    -0.07
    èĪĹ
    -0.07
    etch
    -0.06
    alus
    -0.06
    alley
    -0.06
    stride
    -0.06
    blem
    -0.06
    .createTextNode
    -0.06
    IMITIVE
    -0.06
    POSITIVE LOGITS
     only
    0.11
     ONLY
    0.10
    only
    0.09
    Only
    0.09
     Only
    0.08
     sólo
    0.08
     rare
    0.08
     reserved
    0.07
     ÑĤолÑĮко
    0.07
     limited
    0.07
    Activations Density 0.016%

    No Known Activations