© 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 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. 15-LLAMASCOPE-RES-32K
    11. 29141
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to measurements, quantities, and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idia
    -0.14
    iÄįka
    -0.14
    ickle
    -0.13
    ompiler
    -0.13
    ëļ
    -0.13
     smoothing
    -0.13
    rschein
    -0.13
    adesh
    -0.13
     Amph
    -0.13
    emark
    -0.13
    POSITIVE LOGITS
     called
    0.21
    called
    0.20
    -called
    0.18
    ovsky
    0.17
     termed
    0.17
     llam
    0.16
    hin
    0.16
    Called
    0.16
    ML
    0.16
     tzv
    0.16
    Activations Density 0.008%

    No Known Activations