© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 61285
    Prev
    Next
    INDEX
    Explanations

    sentences that contain forms of the verb "to be."

    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
    493
    -0.07
    dds
    -0.06
    528
    -0.06
    SF
    -0.06
    elda
    -0.06
    ugh
    -0.06
    ients
    -0.06
    ÑĢев
    -0.06
    ikhail
    -0.06
    Clone
    -0.06
    POSITIVE LOGITS
    otope
    0.08
    oe
    0.07
    peria
    0.07
    assi
    0.06
    iris
    0.06
    à¹Ģà¸Ĺ
    0.06
     Demir
    0.06
    uisse
    0.06
     civ
    0.06
    lisi
    0.06
    Activations Density 0.004%

    No Known Activations