© 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. 27938
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to files, documentation, and official content

    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
     Tower
    -0.16
    owell
    -0.15
    anson
    -0.15
    inkel
    -0.14
    829
    -0.14
     d
    -0.14
    .catch
    -0.14
    pton
    -0.14
    .dp
    -0.14
     Mart
    -0.14
    POSITIVE LOGITS
    hausen
    0.18
    ersive
    0.15
    zu
    0.15
    erno
    0.15
    bish
    0.15
    avl
    0.15
    æ©ĭ
    0.14
     ~>
    0.14
    ICO
    0.14
    avn
    0.14
    Activations Density 0.006%

    No Known Activations