© 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. 16211
    Prev
    Next
    INDEX
    Explanations

    command-line instructions and package management terms

    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
    ric
    -0.07
     XPAR
    -0.06
    uko
    -0.06
    ovaly
    -0.06
    aceous
    -0.06
     Lesser
    -0.06
    ymm
    -0.06
    amon
    -0.06
     Huck
    -0.06
    inkle
    -0.06
    POSITIVE LOGITS
     Atkins
    0.07
    á»ı
    0.06
     fores
    0.06
    ControlEvents
    0.06
     defer
    0.06
     sp
    0.06
    ади
    0.06
    roman
    0.06
    (AT
    0.06
     ros
    0.06
    Activations Density 0.000%

    No Known Activations