© 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. 29-LLAMASCOPE-RES-32K
    11. 1731
    Prev
    Next
    INDEX
    Explanations

    sequences that resemble prayers or mantras

    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
     à¤²à¥ľà¤ķ
    -0.23
    à¥ľà¤ķ
    -0.20
    िरफ
    -0.16
    à¥Ģà¤Ĩà¤Ī
    -0.15
    Batch
    -0.15
    arra
    -0.15
    å´
    -0.15
    mach
    -0.15
    ertools
    -0.15
    à¥Īसल
    -0.15
    POSITIVE LOGITS
     Budd
    0.19
     citt
    0.19
     vivid
    0.18
     ca
    0.18
    antasy
    0.17
    iva
    0.17
     ev
    0.16
     DV
    0.16
     param
    0.16
    492
    0.16
    Activations Density 0.009%

    No Known Activations