INDEX

Explanations

phrases indicating potential reductions or optimizations in processes or systems

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

undler

-0.15

xia

-0.15

onder

-0.14

nda

-0.14

vala

-0.14

Compound

-0.14

soles

-0.14

UniqueId

-0.14

umer

-0.13

anj

-0.13

POSITIVE LOGITS

 removing

0.16

 instead

0.16

 ØŃØ°Ùģ

0.15

 Removing

0.15

iones

0.15

erten

0.15

 Simpl

0.15

 simpl

0.15

ãĥĲãĤ¹

0.15

Sk

0.14

Activations Density 0.010%

phrases indicating potential reductions or optimizations in processes or systems

No Comments

No Known Activations