© 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. 27-LLAMASCOPE-RES-32K
    6. 19850
    Prev
    Next
    INDEX
    Explanations

    details about artistic publications and releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unner
    -0.16
    bras
    -0.15
    alue
    -0.15
    obraz
    -0.14
    ulo
    -0.14
    (#)
    -0.14
    HD
    -0.14
     televis
    -0.14
     copyrighted
    -0.14
    rous
    -0.13
    POSITIVE LOGITS
     z
    0.29
     ris
    0.22
    z
    0.22
    Âłz
    0.22
     DIY
    0.20
    =z
    0.19
     diy
    0.19
    [z
    0.18
     ltd
    0.17
    *z
    0.17
    Activations Density 0.031%

    No Known Activations