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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 96065
    Prev
    Next
    INDEX
    Explanations

    mentions of Michael Jackson and related references

    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
    cco
    -0.08
    esser
    -0.08
     æº
    -0.07
    olet
    -0.07
    o
    -0.06
     Dual
    -0.06
     xo
    -0.06
    akit
    -0.06
     ãĤ¢ãĤ¤
    -0.06
    ixel
    -0.06
    POSITIVE LOGITS
    meli
    0.06
    lrt
    0.06
    ollectors
    0.06
    _lon
    0.06
    ucz
    0.06
    prene
    0.06
    adel
    0.06
    atsu
    0.06
    ologie
    0.06
    TM
    0.06
    Activations Density 0.002%

    No Known Activations