© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 91827
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "have" and its variations

    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
    hart
    -0.07
     whom
    -0.06
    µľ
    -0.06
    ---</
    -0.06
     who
    -0.06
    trak
    -0.06
     Ston
    -0.06
     Sommer
    -0.06
     ne
    -0.06
    нин
    -0.05
    POSITIVE LOGITS
    antity
    0.07
    ancements
    0.07
     OTHERWISE
    0.07
    itom
    0.07
    917
    0.07
    ummings
    0.07
    ITIONS
    0.07
    -нибÑĥдÑĮ
    0.06
    athi
    0.06
    æıı
    0.06
    Activations Density 0.019%

    No Known Activations