© 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. 17253
    Prev
    Next
    INDEX
    Explanations

    nouns and terms related to professional roles and organizational transitions

    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
    TECTED
    -0.14
    .TestTools
    -0.13
    _NPC
    -0.11
    ãĥ¼ãĥĬ
    -0.11
    iesen
    -0.11
     rencontres
    -0.10
    uno
    -0.10
    олаг
    -0.10
    εια
    -0.10
    ulence
    -0.10
    POSITIVE LOGITS
     new
    1.32
    new
    1.05
    æĸ°çļĦ
    1.00
    (new
    0.92
    -new
    0.91
    æĸ°
    0.89
    	new
    0.87
    =new
    0.85
     neuen
    0.82
    à¹ĥหม
    0.82
    Activations Density 2.046%

    No Known Activations