© 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. 90058
    Prev
    Next
    INDEX
    Explanations

    actions related to transactions and logistical processes

    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
    avour
    -0.07
    oine
    -0.07
    ser
    -0.07
    ovÃŃ
    -0.07
    senal
    -0.07
    .synthetic
    -0.06
    ìĹIJëıĦ
    -0.06
    _CONST
    -0.06
    άÏģÏĩ
    -0.06
     ìķĦëĭĮ
    -0.06
    POSITIVE LOGITS
     then
    0.09
    ï¼ĮçĦ¶åIJİ
    0.07
    çĦ¶åIJİ
    0.07
    ãģĿãģĹãģ¦
    0.07
    then
    0.07
    idy
    0.06
     rá»ĵi
    0.06
     THEN
    0.06
    fter
    0.06
     briefly
    0.06
    Activations Density 0.051%

    No Known Activations