© 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. 6-LLAMASCOPE-RES-32K
    11. 12752
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to various forms of representation or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ternet
    -0.15
    nten
    -0.14
    defs
    -0.14
    alto
    -0.14
     unt
    -0.14
    emm
    -0.14
    .pkg
    -0.13
     faith
    -0.13
    ĶåĽŀ
    -0.13
    incer
    -0.13
    POSITIVE LOGITS
     to
    0.40
    åĪ°çļĦ
    0.33
    åĪ°
    0.31
     kepada
    0.30
    ToBounds
    0.29
    æĸ¼
    0.28
     Ø¥ÙĦÙī
    0.27
    äºİ
    0.23
    ToFile
    0.23
     Ø¥ÙĦÙĬÙĩ
    0.23
    Activations Density 1.025%

    No Known Activations