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. 10-LLAMASCOPE-RES-32K
    6. 20490
    Prev
    Next
    INDEX
    Explanations

    references to commercial spaces and business-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ấm
    -0.15
    .nasa
    -0.15
    inya
    -0.13
     Brennan
    -0.13
    arpa
    -0.13
    egrated
    -0.13
    adian
    -0.13
     Cox
    -0.13
    ivable
    -0.13
    egis
    -0.13
    POSITIVE LOGITS
    åĤ¬
    0.17
    )new
    0.14
     strips
    0.14
    tru
    0.14
    Strip
    0.14
    fuse
    0.14
    ÏĮν
    0.14
    _CONTINUE
    0.14
    shed
    0.13
    amus
    0.13
    Activations Density 0.051%

    No Known Activations