Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95704
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" in various tenses

    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
    ,[],
    -0.09
    çļĦè¯Ŀ
    -0.08
    zin
    -0.08
     ayrıca
    -0.08
    OUCH
    -0.08
    â̦"↵↵
    -0.08
    maktan
    -0.08
    ÑĩÑĥк
    -0.07
    	Copyright
    -0.07
    Į¨
    -0.07
    POSITIVE LOGITS
     somehow
    0.08
     indeed
    0.07
    ington
    0.07
     something
    0.07
    ida
    0.07
    uala
    0.07
    uite
    0.06
     should
    0.06
     cob
    0.06
    *
    0.06
    Activations Density 0.160%

    No Known Activations