© 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. 40826
    Prev
    Next
    INDEX
    Explanations

    topics related to business and corporate structure

    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
    esson
    -0.07
    urai
    -0.07
    449
    -0.07
    éģ
    -0.06
     trillion
    -0.06
    št
    -0.06
    UMB
    -0.06
    äºĭæĥħ
    -0.06
    removeAttr
    -0.06
    oya
    -0.06
    POSITIVE LOGITS
     proper
    0.07
     itself
    0.07
    /***************************************************************************↵
    0.07
     samot
    0.07
    asad
    0.07
     Ba
    0.06
     Bris
    0.06
    itos
    0.06
    vise
    0.06
    buz
    0.06
    Activations Density 0.161%

    No Known Activations