INDEX

Explanations

programming and technical jargon related to coding structures and components

oai_token-act-pair · gpt-4o-mini Triggered 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

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rrha

-0.14

mÃ®

-0.13

imary

-0.12

rych

-0.12

abbo

-0.12

áº£o

-0.12

xin

-0.12

 addCriterion

-0.12

.MainActivity

-0.11

æĬ¥åĲį

-0.11

POSITIVE LOGITS

âĢ¦↵

0.16

.scalablytyped

0.13

...↵

0.13

0.12

...↵↵↵

0.12

 âĢ¦↵

0.12

LOPT

0.12

pictured

0.11

âĢ¦↵↵

0.11

 [âĢ¦]↵

0.11

Activations Density 5.961%

programming and technical jargon related to coding structures and components

No Comments

No Known Activations