© 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. 25-LLAMASCOPE-RES-32K
    11. 21734
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or hesitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wert
    -0.15
     ná»ķi
    -0.14
    Defaults
    -0.13
    amba
    -0.13
    à¤Ĥà¤ļ
    -0.13
    IDI
    -0.13
    itten
    -0.13
    losion
    -0.13
     Celebrity
    -0.13
    uart
    -0.13
    POSITIVE LOGITS
     called
    0.50
     term
    0.49
     call
    0.49
     termed
    0.48
    称
    0.46
     label
    0.43
     calls
    0.41
    called
    0.41
     gá»įi
    0.41
    稱
    0.40
    Activations Density 0.211%

    No Known Activations