INDEX

Explanations

references to specific games, seasons, and performances in sports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 offseason

-0.15

 next

-0.15

 Ø¨Ø±Ø¯

-0.15

 Goldberg

-0.14

 Batch

-0.14

PDOException

-0.14

 pháº©m

-0.14

 interf

-0.14

 interfering

-0.14

.bind

-0.14

POSITIVE LOGITS

 campaign

0.29

campaign

0.23

Campaign

0.22

 campaigns

0.22

 Campaign

0.21

 regular

0.21

 schedule

0.18

Regular

0.18

regular

0.18

onica

0.17

Activations Density 0.033%

references to specific games, seasons, and performances in sports

No Comments

No Known Activations