© 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. 1936
    Prev
    Next
    INDEX
    Explanations

    numerical data and formatting details, particularly in technical or programming contexts

    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
    icha
    -0.16
     quarter
    -0.14
    ModelProperty
    -0.14
    koli
    -0.14
    emain
    -0.14
    ieten
    -0.14
     Mil
    -0.14
    .fd
    -0.14
     VID
    -0.14
    ģına
    -0.14
    POSITIVE LOGITS
    50
    0.72
     Miller
    0.61
    51
    0.57
    Miller
    0.54
    500
    0.52
     Fifty
    0.52
     fifty
    0.51
    510
    0.47
    505
    0.47
    ÛµÛ°
    0.46
    Activations Density 0.117%

    No Known Activations