© 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. 9-LLAMASCOPE-RES-131K
    11. 95678
    Prev
    Next
    INDEX
    Explanations

    quantities and measurements

    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
    ine
    -0.07
    qm
    -0.06
    ools
    -0.06
    itz
    -0.06
    .asp
    -0.06
     EITHER
    -0.06
    ack
    -0.06
    guards
    -0.06
    oman
    -0.06
    arching
    -0.06
    POSITIVE LOGITS
    etak
    0.08
    /or
    0.08
    otas
    0.07
    okit
    0.07
    аÑĤегоÑĢ
    0.07
    orra
    0.07
    orz
    0.06
    rog
    0.06
    oblin
    0.06
     corresponding
    0.06
    Activations Density 0.063%

    No Known Activations