© 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. 26-LLAMASCOPE-RES-32K
    11. 6344
    Prev
    Next
    INDEX
    Explanations

    references to internet security and privacy issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unal
    -0.16
    ooter
    -0.15
    ople
    -0.15
    otech
    -0.14
     Hass
    -0.14
    æľĢæĸ°
    -0.14
    agate
    -0.14
    anol
    -0.14
    avia
    -0.14
    μÏĢ
    -0.14
    POSITIVE LOGITS
     websites
    0.26
     surfing
    0.25
     browsing
    0.24
     visited
    0.23
     traffic
    0.23
     website
    0.22
    Visited
    0.20
     Websites
    0.20
     sites
    0.20
     activity
    0.20
    Activations Density 0.065%

    No Known Activations