© 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. 20-LLAMASCOPE-RES-32K
    11. 24386
    Prev
    Next
    INDEX
    Explanations

    security-related vulnerabilities and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ker
    -0.15
    iras
    -0.15
    .od
    -0.14
    AsyncResult
    -0.14
    aint
    -0.14
    eur
    -0.14
    ksam
    -0.14
    manuel
    -0.14
    ën
    -0.13
    머ëĭĪ
    -0.13
    POSITIVE LOGITS
    electron
    0.17
    ifest
    0.17
     chrome
    0.16
    ruba
    0.16
     Electron
    0.16
    pch
    0.16
    ovsky
    0.16
    .tp
    0.16
    hta
    0.16
    oloji
    0.16
    Activations Density 0.051%

    No Known Activations