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. 28-LLAMASCOPE-RES-32K
    6. 21280
    Prev
    Next
    INDEX
    Explanations

    questions and expressions of uncertainty regarding troubleshooting or seeking assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ost
    -0.15
    artifact
    -0.15
    ]={↵
    -0.15
    semble
    -0.15
    ivate
    -0.14
    uely
    -0.14
    DataTask
    -0.13
    (æ°´
    -0.13
     Hunt
    -0.13
    nodeName
    -0.13
    POSITIVE LOGITS
     loop
    0.18
     wrote
    0.18
     call
    0.17
     Loop
    0.17
     implements
    0.17
    call
    0.16
     IMPLEMENT
    0.16
    è§Ħå®ļ
    0.16
    loop
    0.16
     Implement
    0.16
    Activations Density 0.206%

    No Known Activations