© 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. 78242
    Prev
    Next
    INDEX
    Explanations

    elements that indicate opinion or subjective judgment

    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
    ãģ®æĸ¹
    -0.06
    ItemSelectedListener
    -0.06
    ¶
    -0.06
     cardinal
    -0.06
     thái
    -0.06
    Å¡ak
    -0.06
    cej
    -0.06
    uesta
    -0.06
    ultimate
    -0.06
     à¤ĩसस
    -0.05
    POSITIVE LOGITS
     Nam
    0.10
    Nam
    0.10
    nam
    0.07
    çľī
    0.07
     Specifically
    0.07
     pun
    0.06
    adir
    0.06
    SingleNode
    0.06
    antly
    0.06
    æ¯ķ
    0.06
    Activations Density 0.184%

    No Known Activations