Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22641
    Prev
    Next
    INDEX
    Explanations

    natural and organic personal care products and their applications

    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
    osg
    -0.15
    .flat
    -0.14
    vale
    -0.14
     Furn
    -0.14
    odesk
    -0.14
    uffman
    -0.14
    nst
    -0.14
    aurus
    -0.14
     respir
    -0.14
     Smoke
    -0.13
    POSITIVE LOGITS
     bath
    0.40
     wash
    0.38
     soap
    0.36
     baths
    0.35
     shower
    0.35
     bat
    0.35
     washing
    0.35
     bathing
    0.34
     Soap
    0.32
     Baths
    0.31
    Activations Density 0.095%

    No Known Activations