© 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. 126923
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "to be" and their forms in various contexts

    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
    .vaadin
    -0.07
    raj
    -0.06
    ordes
    -0.06
    æŃ£åľ¨
    -0.06
    /plain
    -0.06
    apl
    -0.06
    esso
    -0.06
    ami
    -0.06
    ัà¸Ļม
    -0.06
    oui
    -0.06
    POSITIVE LOGITS
    ellen
    0.08
    ailer
    0.07
     able
    0.07
     sure
    0.06
     familiar
    0.06
    atur
    0.06
    adol
    0.06
    etz
    0.06
     Proud
    0.06
     odds
    0.06
    Activations Density 0.029%

    No Known Activations