© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 29137
    Prev
    Next
    INDEX
    Explanations

    programming and code structure elements

    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
    åĩ½
    -0.14
    Subsystem
    -0.13
     Successfully
    -0.13
    BOOLE
    -0.13
    еÑĢап
    -0.12
     trous
    -0.12
     Æ°á»Ľc
    -0.12
    beck
    -0.12
    imple
    -0.12
    ("***
    -0.12
    POSITIVE LOGITS
    axies
    0.15
    ç´Ģ
    0.15
    vero
    0.14
    sth
    0.14
    纪
    0.13
    oru
    0.13
    isy
    0.13
    istrovstvÃŃ
    0.13
    Bindable
    0.13
    .itemView
    0.13
    Activations Density 0.375%

    No Known Activations