INDEX

Explanations

phrases indicating technical issues or troubleshooting steps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ache

-0.16

è¦

-0.15

æ´²

-0.15

.Debugger

-0.15

imir

-0.15

ECTOR

-0.14

jedn

-0.14

 Rach

-0.14

 pager

-0.13

lien

-0.13

POSITIVE LOGITS

aliz

0.15

kav

0.15

 yesterday

0.14

 Ð²Ñĩ

0.14

æĺ¨

0.14

 Entertainment

0.13

 Partition

0.13

 diag

0.13

 entertainment

0.13

 Barber

0.13

Activations Density 0.061%

phrases indicating technical issues or troubleshooting steps

No Comments

No Known Activations