© 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. 13-LLAMASCOPE-RES-32K
    11. 18520
    Prev
    Next
    INDEX
    Explanations

    concerns related to healthcare costs and affordability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aspers
    -0.18
    lasses
    -0.17
    erosis
    -0.16
    BOOLE
    -0.16
    ebe
    -0.15
    VisualStyle
    -0.15
    ï¼ģï¼ģ↵↵
    -0.15
    ektor
    -0.15
    erator
    -0.15
    ascus
    -0.15
    POSITIVE LOGITS
    nest
    0.15
     personal
    0.15
     Conc
    0.15
    uts
    0.15
     TORT
    0.15
    LEE
    0.15
    pline
    0.15
    æľĽ
    0.14
    em
    0.14
    umm
    0.14
    Activations Density 0.046%

    No Known Activations