© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 21-LLAMASCOPE-RES-32K
    11. 19198
    Prev
    Next
    INDEX
    Explanations

    references to health-related topics and the impact of technology on society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ¨
    -0.30
     in
    -0.23
    åľ¨åľ°
    -0.22
     ÙģÙĬ
    -0.21
    æĶ¾åľ¨
    -0.20
     în
    -0.20
    à¹ĥà¸Ļà¸ģาร
    -0.18
    _into
    -0.18
    InThe
    -0.18
     åľ¨
    -0.17
    POSITIVE LOGITS
     ÙĪÙģÙĬ
    0.25
     context
    0.22
     guise
    0.21
    /on
    0.19
     circles
    0.19
     fashion
    0.19
     contexts
    0.18
     terms
    0.18
    context
    0.18
     manner
    0.17
    Activations Density 1.166%

    No Known Activations