Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96035
    Prev
    Next
    INDEX
    Explanations

    references to global or widespread impact

    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
    oga
    -0.06
    veillance
    -0.06
     Absolute
    -0.06
    uria
    -0.06
     absolut
    -0.06
    idth
    -0.06
    wick
    -0.05
    tera
    -0.05
     constructs
    -0.05
    à¥Ĥत
    -0.05
    POSITIVE LOGITS
    idel
    0.07
    λαν
    0.07
    Ú¯ÙĪ
    0.07
    792
    0.07
    è¦
    0.07
    LinkId
    0.07
    ResultsController
    0.07
    iana
    0.06
    IRO
    0.06
    ermo
    0.06
    Activations Density 0.016%

    No Known Activations