© 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. 41165
    Prev
    Next
    INDEX
    Explanations

    expressions of value or worth

    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
    statt
    -0.08
    tera
    -0.07
    ÙĩÙĨ
    -0.07
    ConverterFactory
    -0.07
    raq
    -0.07
     ÑĤабли
    -0.07
    optera
    -0.07
    ulpt
    -0.07
    shouldBe
    -0.07
    ôm
    -0.07
    POSITIVE LOGITS
     for
    0.08
     if
    0.07
     Worth
    0.07
     to
    0.06
     worth
    0.06
    614
    0.06
     considering
    0.06
     consideration
    0.06
     Expires
    0.06
     when
    0.06
    Activations Density 0.011%

    No Known Activations