© 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. 10972
    Prev
    Next
    INDEX
    Explanations

    phrases related to the theme of community and its significance

    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
    ow
    -0.16
    adelphia
    -0.15
    iju
    -0.14
    ubat
    -0.14
    /licenses
    -0.14
    ina
    -0.14
    ť
    -0.14
    kest
    -0.14
     Tong
    -0.14
    addon
    -0.13
    POSITIVE LOGITS
     expense
    0.50
     Expense
    0.42
    expense
    0.40
     at
    0.39
     expenses
    0.33
    Expense
    0.31
     cost
    0.29
     Kosten
    0.29
     Expenses
    0.28
     detriment
    0.28
    Activations Density 0.082%

    No Known Activations