© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 18706
    Prev
    Next
    INDEX
    Explanations

    themes related to ambition and resilience

    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
    ãĢĭï¼Į
    -0.14
    .)↵↵↵↵
    -0.13
    ï¼īãĢģ
    -0.13
    ï¼ģãĢį
    -0.13
    ï¼ģ”
    -0.13
    .),
    -0.12
    .);↵
    -0.12
    "),"
    -0.12
    åĴĮ
    -0.12
    ãĢįï¼Į
    -0.12
    POSITIVE LOGITS
    ,
    0.91
    ,↵
    0.41
     ,
    0.39
    ,...↵
    0.38
    ®,
    0.35
    ี,
    0.34
    -,
    0.32
    à¹Į,
    0.32
    ,in
    0.29
    à¥Ģ,
    0.29
    Activations Density 3.992%

    No Known Activations