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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 4-LLAMASCOPE-RES-32K
    11. 30691
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to limits and bounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ube
    -0.17
    ondo
    -0.16
    rica
    -0.14
    erval
    -0.14
     dang
    -0.14
     Kit
    -0.14
    351
    -0.14
    terminal
    -0.14
    YLES
    -0.14
    330
    -0.13
    POSITIVE LOGITS
    aho
    0.14
     ine
    0.14
    جة
    0.14
    鬼
    0.13
    burn
    0.13
    fre
    0.13
    bon
    0.13
     inhal
    0.13
     Fey
    0.13
    ched
    0.13
    Activations Density 0.065%

    No Known Activations