© 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. 105463
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "be" in various forms

    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
    -sama
    -0.07
     اعتÙħاد
    -0.07
    845
    -0.06
    cura
    -0.06
    ceptive
    -0.06
    kers
    -0.06
    arrant
    -0.06
    оÑĪ
    -0.06
    åĽ
    -0.06
     Uhr
    -0.06
    POSITIVE LOGITS
    atus
    0.07
    ATAL
    0.07
    be
    0.07
    YRO
    0.06
    atitude
    0.06
    ATUS
    0.06
    isay
    0.06
     familiar
    0.06
    jer
    0.06
    otel
    0.06
    Activations Density 0.013%

    No Known Activations