© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 105657
    Prev
    Next
    INDEX
    Explanations

    references to surveys and statistics about small and medium enterprises (SMEs)

    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
    verty
    -0.07
    pone
    -0.07
    овÑĸд
    -0.07
    .lab
    -0.07
    oyer
    -0.06
     оз
    -0.06
    FY
    -0.06
    zens
    -0.06
    pie
    -0.06
    aad
    -0.06
    POSITIVE LOGITS
     Opinion
    0.08
     opinions
    0.07
     opinion
    0.07
     attitudes
    0.07
     anonymously
    0.07
     opin
    0.06
     randomly
    0.06
     ÙĪاس
    0.06
    /jav
    0.06
    ByKey
    0.06
    Activations Density 0.015%

    No Known Activations