Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 15272
    Prev
    Next
    INDEX
    Explanations

    references to specific dates or timeframes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    YTE
    -0.18
    patch
    -0.16
    arLayout
    -0.16
    olie
    -0.15
    Patch
    -0.14
     Patch
    -0.14
    олом
    -0.14
    esa
    -0.14
    tik
    -0.14
    ữ
    -0.14
    POSITIVE LOGITS
     flood
    0.43
     flooding
    0.41
     Flood
    0.37
     floods
    0.36
     flooded
    0.34
     Flo
    0.32
    Flo
    0.30
     inund
    0.25
     flash
    0.23
    lood
    0.22
    Activations Density 0.000%

    No Known Activations