© 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. 26444
    Prev
    Next
    INDEX
    Explanations

    numeric values related to data, likely in a structured or formal context

    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
    018
    -0.07
    ite
    -0.07
    ало
    -0.06
    ì§ķ
    -0.06
    égor
    -0.06
    и
    -0.06
    mont
    -0.06
    alls
    -0.06
    021
    -0.06
    ãĥ¼ãĥ
    -0.06
    POSITIVE LOGITS
    #ad
    0.07
    #ab
    0.07
    çak
    0.06
    Äįer
    0.06
    utters
    0.06
    uÃŃ
    0.06
    'gc
    0.06
    گاÙĨ
    0.06
     useStyles
    0.06
    awai
    0.06
    Activations Density 0.010%

    No Known Activations