© 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. 29-LLAMASCOPE-RES-32K
    11. 15751
    Prev
    Next
    INDEX
    Explanations

    adjectives and phrases indicating non-harmful and hypoallergenic qualities in products

    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
    uter
    -0.16
    å§
    -0.14
    omics
    -0.14
     Dann
    -0.14
    agner
    -0.14
    avors
    -0.14
     Ernst
    -0.13
    bus
    -0.13
    å¹
    -0.13
     Bath
    -0.13
    POSITIVE LOGITS
     toxic
    0.23
     harsh
    0.21
     abrasive
    0.19
    abras
    0.19
     harmful
    0.19
     hazardous
    0.19
     invasive
    0.19
     irritating
    0.18
     gre
    0.18
     conduct
    0.18
    Activations Density 0.097%

    No Known Activations