© 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. 29-LLAMASCOPE-RES-32K
    11. 12812
    Prev
    Next
    INDEX
    Explanations

    concepts related to processes and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dae
    -0.13
    ίÏīν
    -0.13
    722
    -0.13
    zcze
    -0.13
    lice
    -0.13
    riot
    -0.13
    stvÃŃ
    -0.13
    ovel
    -0.12
    [param
    -0.12
    (prompt
    -0.12
    POSITIVE LOGITS
     process
    1.03
    process
    0.90
     Process
    0.82
     proces
    0.78
    -process
    0.75
    Process
    0.74
    _process
    0.73
     processes
    0.73
     PROCESS
    0.71
     processo
    0.70
    Activations Density 0.308%

    No Known Activations