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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-32K
    6. 10701
    Prev
    Next
    INDEX
    Explanations

    references to antioxidants and their health benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assium
    -0.16
    imestone
    -0.14
     automát
    -0.14
     uranium
    -0.14
    ecimal
    -0.14
    dna
    -0.14
    ISCO
    -0.14
     Salt
    -0.13
    salt
    -0.13
    ilege
    -0.13
    POSITIVE LOGITS
     lign
    0.25
     monot
    0.24
     ses
    0.23
     ter
    0.23
     cou
    0.23
     flav
    0.22
     phen
    0.22
     bios
    0.21
     phy
    0.21
     caffe
    0.21
    Activations Density 0.072%

    No Known Activations