© 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. 20-LLAMASCOPE-RES-32K
    11. 29069
    Prev
    Next
    INDEX
    Explanations

    elements related to animals and their interactions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĵn
    -0.16
    ugar
    -0.15
    jez
    -0.14
     Macros
    -0.14
    ãĥĥãĥī
    -0.14
    rain
    -0.14
    507
    -0.14
    509
    -0.13
    533
    -0.13
    utas
    -0.13
    POSITIVE LOGITS
     loose
    0.57
     Loose
    0.47
     released
    0.33
    /loose
    0.33
     release
    0.33
     free
    0.33
     unleashed
    0.31
    Released
    0.30
    _Release
    0.30
     Released
    0.29
    Activations Density 0.166%

    No Known Activations