© 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. 14-LLAMASCOPE-RES-32K
    11. 22728
    Prev
    Next
    INDEX
    Explanations

    terms related to procedural regulations and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¤ãĤ¯
    -0.15
    anna
    -0.14
    /dir
    -0.14
    iosis
    -0.14
    okrat
    -0.14
    udy
    -0.13
    iqu
    -0.13
    unta
    -0.13
    ằm
    -0.13
    _HAL
    -0.12
    POSITIVE LOGITS
     still
    0.43
    still
    0.40
    ä»į
    0.40
     Still
    0.36
    Still
    0.35
     unchanged
    0.35
     vẫn
    0.34
     continue
    0.34
     continues
    0.32
     STILL
    0.32
    Activations Density 0.338%

    No Known Activations