© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77595
    Prev
    Next
    INDEX
    Explanations

    phrases that express obtaining knowledge or experience

    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
    á»Ļc
    -0.07
    .bam
    -0.07
    讯
    -0.07
    ısından
    -0.07
     fChain
    -0.07
    alink
    -0.07
    vailability
    -0.06
    avra
    -0.06
    бо
    -0.06
     اÙĦتص
    -0.06
    POSITIVE LOGITS
     understanding
    0.09
     impression
    0.08
     view
    0.08
     insight
    0.08
     glimpse
    0.07
     upper
    0.06
    äºĨè§£
    0.06
     understand
    0.06
     sense
    0.06
     idea
    0.06
    Activations Density 0.020%

    No Known Activations