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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 41995
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "have."

    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
     itself
    -0.14
    ska
    -0.10
    s
    -0.10
    nya
    -0.09
    rael
    -0.08
    nyder
    -0.08
    ãĤ£
    -0.08
    gnore
    -0.08
    den
    -0.08
    loader
    -0.08
    POSITIVE LOGITS
     themselves
    0.18
     yourselves
    0.09
     their
    0.09
     thems
    0.08
    lessly
    0.08
    edException
    0.07
     Their
    0.07
    able
    0.07
    ìĦľ
    0.07
     selves
    0.07
    Activations Density 0.119%

    No Known Activations