© 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. 20-LLAMASCOPE-RES-32K
    11. 16640
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to organizational structure and management practices

    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
     rather
    -0.54
    rather
    -0.46
     chứ
    -0.40
     Rather
    -0.38
    ãģ§ãģ¯ãģªãģı
    -0.35
    Rather
    -0.33
     plutôt
    -0.30
     statt
    -0.28
     instead
    -0.27
    instead
    -0.25
    POSITIVE LOGITS
     anymore
    0.23
     which
    0.23
     necessarily
    0.21
    (which
    0.21
     alone
    0.19
    which
    0.19
     Which
    0.18
     like
    0.17
     usual
    0.17
    wich
    0.17
    Activations Density 0.200%

    No Known Activations