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 (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 20688
    Prev
    Next
    INDEX
    Explanations

    phrases related to business growth and community engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desn
    -0.17
    adera
    -0.16
    ắc
    -0.15
    ãĥ¼ãĤ¸
    -0.14
    805
    -0.14
    iage
    -0.14
    {text
    -0.14
     endregion
    -0.14
     consts
    -0.14
    itere
    -0.14
    POSITIVE LOGITS
     chance
    0.19
     opportunity
    0.18
     enough
    0.16
    hv
    0.16
     chances
    0.16
    enis
    0.15
    ifferent
    0.15
     perfect
    0.15
     satisfying
    0.14
     required
    0.14
    Activations Density 0.152%

    No Known Activations