Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84284
    Prev
    Next
    INDEX
    Explanations

    phrases indicating motion or change in state

    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
    ãĥ©ãĤ¯
    -0.06
    _DYNAMIC
    -0.06
    HeaderValue
    -0.06
    racat
    -0.06
    /loose
    -0.06
     ={↵
    -0.05
    ãĤ©
    -0.05
    ADM
    -0.05
    имо
    -0.05
     mun
    -0.05
    POSITIVE LOGITS
    -turned
    0.09
    -than
    0.08
    ãģĵãģĿ
    0.07
    .blogspot
    0.07
    .com
    0.07
    enor
    0.07
    bsp
    0.07
    ongsTo
    0.07
    upertino
    0.07
    nbsp
    0.06
    Activations Density 0.060%

    No Known Activations