INDEX

Explanations

references to time and scheduling details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

abee

-0.15

athers

-0.15

ags

-0.14

 Huffman

-0.14

JR

-0.14

 Shock

-0.14

Ĥ¬

-0.14

 TomÃ¡Å¡

-0.13

Boo

-0.13

ulling

-0.13

POSITIVE LOGITS

heel

0.16

åģ¥

0.15

IELD

0.14

_esc

0.14

 Needle

0.14

 bekl

0.14

 Ð±Ð¾Ðº

0.14

ç´¯

0.14

ilar

0.14

 showDialog

0.13

Activations Density 0.008%

references to time and scheduling details

No Comments

No Known Activations