© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 24-LLAMASCOPE-RES-32K
    11. 11875
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic growth and industry development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    196
    -0.22
    197
    -0.20
     Victorian
    -0.18
    186
    -0.18
    181
    -0.18
    TV
    -0.17
    Û±Û¹Û¶
    -0.17
     computer
    -0.17
     hass
    -0.16
     nineteenth
    -0.16
    POSITIVE LOGITS
    193
    0.63
    192
    0.54
     Depression
    0.43
     depression
    0.33
     WW
    0.31
     Nazi
    0.28
     Hitler
    0.26
     twenties
    0.26
     Nazis
    0.26
    Û±Û¹
    0.25
    Activations Density 0.272%

    No Known Activations