© 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. 86339
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" in various forms indicating it is monitoring statements of existence or identity

    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
    vant
    -0.06
     DevComponents
    -0.06
    strom
    -0.06
    enden
    -0.06
    .Ticks
    -0.06
     *__
    -0.06
    itm
    -0.06
     partly
    -0.06
    .FontStyle
    -0.06
    oren
    -0.06
    POSITIVE LOGITS
     called
    0.25
    called
    0.23
     Called
    0.18
    Called
    0.18
    -called
    0.17
    åı«
    0.16
     llam
    0.16
     termed
    0.14
     named
    0.14
     olan
    0.13
    Activations Density 0.004%

    No Known Activations