© 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. 3728
    Prev
    Next
    INDEX
    Explanations

    the verb "be" in various forms and 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
    èĥ½å¤Ł
    -0.10
    èĥ½
    -0.08
     kunnen
    -0.07
    меÑĤÑĮ
    -0.07
    amient
    -0.07
     بتÙĪاÙĨ
    -0.07
    lÃŃ
    -0.07
    anas
    -0.07
    anke
    -0.07
    contre
    -0.06
    POSITIVE LOGITS
     easily
    0.13
     Easily
    0.09
    ’t
    0.09
    opies
    0.08
     safely
    0.08
    ÃŃt
    0.08
    't
    0.08
    ister
    0.08
    adians
    0.07
    isters
    0.07
    Activations Density 0.073%

    No Known Activations