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. 24-LLAMASCOPE-RES-32K
    6. 18039
    Prev
    Next
    INDEX
    Explanations

    terms related to therapies and massage techniques for physical ailments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ноÑģÑı
    -0.19
     Chall
    -0.15
     acid
    -0.15
     transparent
    -0.15
    Urls
    -0.15
     vir
    -0.14
    transparent
    -0.14
    urls
    -0.14
     merchant
    -0.14
    aft
    -0.14
    POSITIVE LOGITS
     massage
    0.32
     Massage
    0.29
    Massage
    0.26
    massage
    0.25
     massages
    0.23
    itsu
    0.22
    assage
    0.21
     lymph
    0.21
     masse
    0.20
     ì¶ľìŀ¥
    0.20
    Activations Density 0.050%

    No Known Activations