© 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. 17-LLAMASCOPE-RES-131K
    11. 70999
    Prev
    Next
    INDEX
    Explanations

    technical instructions and guidance related to software development and dependency management

    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
    urd
    -0.08
    ivre
    -0.07
    icine
    -0.07
    _ACTIV
    -0.07
    automatic
    -0.07
    leh
    -0.07
    iec
    -0.07
    ">ÃĹ</
    -0.07
     Relief
    -0.06
     Dillon
    -0.06
    POSITIVE LOGITS
     change
    0.10
     changes
    0.09
    change
    0.09
     changed
    0.09
    _change
    0.08
    /change
    0.08
    Change
    0.07
     changing
    0.07
     Change
    0.07
     cambio
    0.07
    Activations Density 0.012%

    No Known Activations