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. 27-LLAMASCOPE-RES-32K
    6. 110
    Prev
    Next
    INDEX
    Explanations

    achievements and statistics related to sports teams and players

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    628
    -0.18
    ekim
    -0.17
    æķ¦
    -0.16
    iah
    -0.15
     scrut
    -0.15
     unge
    -0.14
     dedi
    -0.14
    BoxLayout
    -0.14
    assis
    -0.14
    esti
    -0.13
    POSITIVE LOGITS
     conference
    0.43
     league
    0.37
     Conference
    0.36
    conference
    0.33
    Conference
    0.32
     conferences
    0.31
     Big
    0.30
     League
    0.28
    -league
    0.28
     конÑĦеÑĢен
    0.27
    Activations Density 0.072%

    No Known Activations