© 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. 60744
    Prev
    Next
    INDEX
    Explanations

    instances of naming and renaming entities in text

    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
    epy
    -0.07
    ÙĦÙĬÙĩ
    -0.07
    اصÙĦ
    -0.06
    seau
    -0.06
    ubber
    -0.06
    lien
    -0.06
    ONGO
    -0.06
    APON
    -0.06
    UND
    -0.06
    alta
    -0.06
    POSITIVE LOGITS
     simply
    0.07
     '
    0.07
    ans
    0.06
    _PTR
    0.06
     something
    0.06
    oons
    0.06
    ISE
    0.06
     â
    0.06
     XD
    0.06
     accordingly
    0.06
    Activations Density 0.011%

    No Known Activations