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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-32K
    6. 2794
    Prev
    Next
    INDEX
    Explanations

    CSS properties and values related to flexbox layout

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acht
    -0.18
    vertisement
    -0.15
    rous
    -0.14
    rien
    -0.14
    æĬŀ
    -0.14
    pants
    -0.14
    IALOG
    -0.14
    TEGER
    -0.14
    vanced
    -0.14
    ç¤
    -0.14
    POSITIVE LOGITS
    avl
    0.15
    extensions
    0.15
    uhl
    0.15
     vak
    0.14
    545
    0.14
    uger
    0.14
     extension
    0.14
    ombat
    0.14
    251
    0.14
     Berry
    0.14
    Activations Density 0.004%

    No Known Activations