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. 20-LLAMASCOPE-RES-32K
    6. 11438
    Prev
    Next
    INDEX
    Explanations

    words related to themes in art and education that involve social or political issues

    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
    es
    -0.16
     Irving
    -0.14
    ables
    -0.14
    affen
    -0.14
    orWhere
    -0.14
     lep
    -0.14
    ive
    -0.14
     Hughes
    -0.13
    ees
    -0.13
    ad
    -0.13
    POSITIVE LOGITS
    ize
    0.25
    -out
    0.21
    iate
    0.20
    ted
    0.19
    -up
    0.19
    ify
    0.19
     lại
    0.18
    elize
    0.18
     out
    0.18
    IZE
    0.16
    Activations Density 0.363%

    No Known Activations