© 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. 10-LLAMASCOPE-RES-32K
    11. 3104
    Prev
    Next
    INDEX
    Explanations

    references to statistical analysis and educational assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    веÑī
    -0.15
     æľŁ
    -0.15
     ëĭ¤ìļ´ë°Ľê¸°
    -0.15
    QN
    -0.15
    iero
    -0.15
    ropolis
    -0.15
    antor
    -0.15
    çī¹èī²
    -0.15
    รà¸ĵ
    -0.14
    peer
    -0.14
    POSITIVE LOGITS
     ebenfalls
    0.17
     Brand
    0.15
    arris
    0.15
    acha
    0.15
    _Helper
    0.15
    les
    0.14
    uala
    0.14
    utzer
    0.14
    637
    0.14
    brand
    0.13
    Activations Density 1.031%

    No Known Activations