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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 27-LLAMASCOPE-RES-32K
    11. 2153
    Prev
    Next
    INDEX
    Explanations

    details related to a specific product, particularly its features and specifications

    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
     drums
    -0.16
    ãģĭãģij
    -0.14
    urre
    -0.14
    оби
    -0.14
     steam
    -0.14
    ute
    -0.14
     drum
    -0.14
    uzzi
    -0.14
    .Dot
    -0.13
    ÑĢаÑħ
    -0.13
    POSITIVE LOGITS
     knife
    0.43
     knives
    0.41
     Knife
    0.36
     blade
    0.35
     blades
    0.34
    knife
    0.32
    Knife
    0.32
     Blades
    0.29
     folders
    0.28
     folder
    0.28
    Activations Density 0.016%

    No Known Activations