© 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. 9-LLAMASCOPE-RES-32K
    6. 26593
    Prev
    Next
    INDEX
    Explanations

    compliance and reporting language in a professional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inous
    -0.15
     \↵
    -0.15
    imli
    -0.15
    \↵
    -0.15
    ]={↵
    -0.14
     ÑģаÑħ
    -0.14
    è¿Ķ
    -0.13
     Dann
    -0.13
    lahoma
    -0.13
    .plist
    -0.13
    POSITIVE LOGITS
    arpa
    0.17
    anden
    0.15
    ̣
    0.15
    oret
    0.15
    zheimer
    0.13
    eken
    0.13
    _CLR
    0.13
    _CLEAN
    0.13
     tone
    0.13
    SBATCH
    0.13
    Activations Density 0.167%

    No Known Activations