© 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. 13-LLAMASCOPE-RES-32K
    11. 26092
    Prev
    Next
    INDEX
    Explanations

    alphanumeric patterns and structures often found in URLs or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    u
    -0.18
    inn
    -0.16
    uu
    -0.15
    ICODE
    -0.15
    /weather
    -0.14
    ãĥ«ãĤ¯
    -0.14
    heat
    -0.14
    uat
    -0.14
    ÏĦεÏħ
    -0.14
    achat
    -0.13
    POSITIVE LOGITS
     Milf
    0.18
    âm
    0.16
    avras
    0.16
     Zem
    0.14
    #
    0.14
    ifter
    0.14
    æ²
    0.14
    .FlatStyle
    0.14
     dil
    0.13
    endale
    0.13
    Activations Density 0.014%

    No Known Activations