© 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. 15-LLAMASCOPE-RES-131K
    11. 89088
    Prev
    Next
    INDEX
    Explanations

    statements related to disclaimers and the limitations of services or products

    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
    renc
    -0.06
    zes
    -0.06
     fopen
    -0.06
    \Common
    -0.06
     gates
    -0.06
    abez
    -0.06
     gate
    -0.06
     unb
    -0.06
     Lester
    -0.06
    athi
    -0.05
    POSITIVE LOGITS
    omatic
    0.07
    ucht
    0.07
    åħ¬å¼ı
    0.07
    iglia
    0.07
    ocaly
    0.07
    å¨ĺ
    0.07
    ãģ£ãģ¡
    0.07
    jom
    0.07
    åĢī
    0.07
    ourd
    0.07
    Activations Density 0.001%

    No Known Activations