© 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. 16148
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their personal circumstances or struggles

    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
     Ấ
    -0.08
    üçük
    -0.08
    ssa
    -0.07
     NSStringFromClass
    -0.07
    DirectoryName
    -0.07
    senal
    -0.07
    aviors
    -0.07
    essa
    -0.07
    stery
    -0.07
    911
    -0.07
    POSITIVE LOGITS
     Cabinet
    0.08
     personal
    0.07
     phot
    0.07
     campaign
    0.07
     secret
    0.06
     cabinet
    0.06
     Vanity
    0.06
     public
    0.06
     private
    0.06
     wife
    0.06
    Activations Density 0.001%

    No Known Activations