© 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. 29-LLAMASCOPE-RES-32K
    6. 19283
    Prev
    Next
    INDEX
    Explanations

    numeric data and statistics related to health and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lesb
    -0.18
     Locale
    -0.18
    LocalStorage
    -0.17
     Leak
    -0.16
     Lod
    -0.16
     Loren
    -0.16
    Lens
    -0.16
    alink
    -0.16
    438
    -0.15
     Leonard
    -0.15
    POSITIVE LOGITS
    liter
    0.66
    -liter
    0.66
    Liter
    0.65
     literature
    0.65
     liter
    0.64
     Liter
    0.62
     Literature
    0.58
     lit
    0.58
    -l
    0.54
     Lit
    0.51
    Activations Density 0.079%

    No Known Activations