© 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. 126305
    Prev
    Next
    INDEX
    Explanations

    terms and abbreviations related to business and finance

    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
    arend
    -0.07
    avenport
    -0.07
    slaught
    -0.07
    okino
    -0.07
    folio
    -0.07
    arkin
    -0.07
    auer
    -0.06
    ãĥ³ãĤ¯
    -0.06
    cherche
    -0.06
    _mD
    -0.06
    POSITIVE LOGITS
     company
    0.08
     parent
    0.07
    www
    0.06
     corporation
    0.06
    åħ¬åı¸
    0.06
     firm
    0.06
    company
    0.06
    YRO
    0.06
     Company
    0.06
    logo
    0.05
    Activations Density 0.022%

    No Known Activations