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. 29-LLAMASCOPE-RES-32K
    6. 3132
    Prev
    Next
    INDEX
    Explanations

    terms related to compliance and security in healthcare contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å³°
    -0.15
    WWW
    -0.14
    Insets
    -0.13
     nÃło
    -0.13
    æĹ¦
    -0.13
    .lu
    -0.13
    ,readonly
    -0.13
    /Dk
    -0.13
     afflicted
    -0.13
    .spy
    -0.13
    POSITIVE LOGITS
     state
    0.54
    state
    0.42
     advanced
    0.41
     cutting
    0.38
     leading
    0.38
    -state
    0.36
    (state
    0.35
    .state
    0.35
     State
    0.34
    advanced
    0.32
    Activations Density 0.556%

    No Known Activations