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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10055
    Prev
    Next
    INDEX
    Explanations

    references to counterfeit products and discussions about their implications

    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
    ARRIER
    -0.14
    tick
    -0.14
    _extract
    -0.14
    Å¡Å¥
    -0.14
    rending
    -0.14
    æĸĻ
    -0.13
     extract
    -0.13
    309
    -0.13
    æ±½
    -0.13
     extraction
    -0.13
    POSITIVE LOGITS
     counter
    0.50
     Counter
    0.47
    counter
    0.46
    -counter
    0.46
    Counter
    0.43
     counterfeit
    0.42
     knock
    0.38
    _counter
    0.36
    .counter
    0.36
    .Counter
    0.35
    Activations Density 0.059%

    No Known Activations