© 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. 3270
    Prev
    Next
    INDEX
    Explanations

    specific details about mussels and their ecological roles

    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
    rzy
    -0.09
    tors
    -0.07
     tors
    -0.07
    oge
    -0.07
    raq
    -0.06
     Invent
    -0.06
    utation
    -0.06
     handling
    -0.06
    vault
    -0.06
    inqu
    -0.06
    POSITIVE LOGITS
     symb
    0.08
    ÑĢоÑģÑĤ
    0.07
     íĭ
    0.07
    çĶŁæ´»
    0.07
    issy
    0.06
    ãĥ¼ãĥĬ
    0.06
    ymb
    0.06
    ноÑĩ
    0.06
     growth
    0.06
     stationary
    0.06
    Activations Density 0.004%

    No Known Activations