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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25-LLAMASCOPE-RES-32K
    6. 22640
    Prev
    Next
    INDEX
    Explanations

    fundamental components and key concepts that contribute to success in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    something
    -0.16
    another
    -0.15
     another
    -0.14
    åı¦ä¸Ģ
    -0.14
    å¨
    -0.14
     prevState
    -0.13
    رÛĮÙĤ
    -0.13
     others
    -0.13
     something
    -0.13
     Another
    -0.13
    POSITIVE LOGITS
     successful
    0.35
     any
    0.32
    successful
    0.29
     every
    0.29
     modern
    0.28
     Successful
    0.28
    Successful
    0.27
     succes
    0.26
     success
    0.25
    æĪIJåĬŁ
    0.25
    Activations Density 0.303%

    No Known Activations