© 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. 57094
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant financial transactions or considerations

    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
    rib
    -0.07
    ondo
    -0.06
    ELLOW
    -0.06
    ÑģÑıÑĩ
    -0.06
    =".$_
    -0.06
    leh
    -0.06
    976
    -0.06
    lh
    -0.06
    ă
    -0.06
     “â̦
    -0.05
    POSITIVE LOGITS
    çİ
    0.07
    atonin
    0.07
    202
    0.06
     صÙĨد
    0.06
     Vaccine
    0.06
    psilon
    0.06
    (Op
    0.06
    edly
    0.06
    aÄĩ
    0.06
    çŃ
    0.06
    Activations Density 0.000%

    No Known Activations