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. 30-LLAMASCOPE-RES-32K
    6. 8419
    Prev
    Next
    INDEX
    Explanations

    references to refugee and detention contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QUIT
    -0.16
    LINK
    -0.15
    herits
    -0.14
     cabinets
    -0.14
    ouz
    -0.14
    庫
    -0.14
    agog
    -0.14
    ecta
    -0.14
     Cabinets
    -0.14
    Inspectable
    -0.13
    POSITIVE LOGITS
     camp
    0.49
     camps
    0.46
     Camp
    0.39
     tent
    0.35
    camp
    0.34
    Camp
    0.34
     enc
    0.34
    tent
    0.28
     tents
    0.28
     Tent
    0.27
    Activations Density 0.042%

    No Known Activations