© 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. 25-LLAMASCOPE-RES-32K
    11. 22453
    Prev
    Next
    INDEX
    Explanations

    references to railway companies and infrastructure

    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
    /GPL
    -0.15
    erland
    -0.15
    ppe
    -0.14
    stration
    -0.14
    íı¬
    -0.14
     cuck
    -0.14
    croft
    -0.14
    olet
    -0.14
    IRS
    -0.14
    430
    -0.14
    POSITIVE LOGITS
     UP
    0.17
     GP
    0.16
     Yard
    0.16
     Juni
    0.16
    ulu
    0.16
     freight
    0.15
     CS
    0.15
     Reconstruction
    0.15
    _GP
    0.15
     reporting
    0.15
    Activations Density 0.019%

    No Known Activations