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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-32K
    11. 2075
    Prev
    Next
    INDEX
    Explanations

    expressions related to starting anew or rebuilding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¼Ļ
    -0.16
     Converted
    -0.15
    542
    -0.14
    仲
    -0.13
     maturity
    -0.13
    datagrid
    -0.13
    phia
    -0.13
    ucci
    -0.13
    ãĥ¼ãĥģ
    -0.13
    manent
    -0.13
    POSITIVE LOGITS
     fresh
    0.49
    fresh
    0.42
     starting
    0.41
     Fresh
    0.38
    Fresh
    0.36
    starting
    0.34
     completely
    0.33
     start
    0.31
     Starting
    0.31
     freshly
    0.30
    Activations Density 0.210%

    No Known Activations