© 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. 94329
    Prev
    Next
    INDEX
    Explanations

    code snippets and references to programming functions or commands

    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
     conced
    -0.07
    å®ĭä½ĵ
    -0.06
    ichick
    -0.06
    obus
    -0.06
    otal
    -0.06
    commons
    -0.06
    ocache
    -0.06
    xad
    -0.06
    igure
    -0.06
    ethyst
    -0.06
    POSITIVE LOGITS
     SHALL
    0.07
    à¤Łà¤ķ
    0.07
    寸
    0.07
     UCHAR
    0.06
    ,},↵
    0.06
     Computing
    0.06
    è¦
    0.06
    aktu
    0.06
    anga
    0.06
    /src
    0.06
    Activations Density 0.007%

    No Known Activations