© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 128458
    Prev
    Next
    INDEX
    Explanations

    quotes and reported speech

    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
    æ°¸ä¹ħ
    -0.08
    estroy
    -0.07
    iren
    -0.07
    tep
    -0.07
    ignet
    -0.07
    -toggler
    -0.07
    leme
    -0.07
    USES
    -0.07
     genders
    -0.06
    ignKey
    -0.06
    POSITIVE LOGITS
     example
    0.07
     examples
    0.07
     analog
    0.07
     explanation
    0.07
    .scalablytyped
    0.06
    615
    0.06
     mean
    0.06
     Lý
    0.06
    REFIX
    0.06
     exp
    0.06
    Activations Density 0.018%

    No Known Activations