© 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. 15-LLAMASCOPE-RES-131K
    11. 27094
    Prev
    Next
    INDEX
    Explanations

    specific technical details and measurements in scientific or analytical contexts

    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
    uan
    -0.08
    Ø¡
    -0.08
    uin
    -0.07
    ocs
    -0.06
    sha
    -0.06
     Scha
    -0.06
     itself
    -0.06
    haps
    -0.06
    ush
    -0.06
    åŁ
    -0.05
    POSITIVE LOGITS
     respectively
    0.26
     respective
    0.18
    åĪĨåĪ«
    0.17
     ÑģооÑĤвеÑĤ
    0.16
    respect
    0.14
     ê°ģê°ģ
    0.12
    ãģĿãĤĮ
    0.11
     вÑĸдповÑĸдно
    0.10
     sıras
    0.09
     correspond
    0.08
    Activations Density 0.062%

    No Known Activations