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. 27-LLAMASCOPE-RES-32K
    6. 11811
    Prev
    Next
    INDEX
    Explanations

    specific numerical values and mathematical expressions throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ../../../
    -0.29
    fold
    -0.23
    ../../
    -0.23
    th
    -0.20
    ../
    -0.19
    ingly
    -0.18
    ante
    -0.17
    обÑĢаз
    -0.17
    furt
    -0.16
    fall
    -0.15
    POSITIVE LOGITS
    nd
    0.66
    nds
    0.35
    ND
    0.34
    -thirds
    0.34
     nd
    0.28
    gether
    0.27
     thirds
    0.26
    ï¸ı
    0.25
     dozen
    0.25
    nder
    0.25
    Activations Density 0.438%

    No Known Activations