INDEX

Explanations

references to specific months and date-related information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uto

-0.17

UTO

-0.15

ollar

-0.15

\Annotation

-0.15

ombie

-0.15

.feedback

-0.13

 Hearts

-0.13

Ø¶ÙĦ

-0.13

Pr

-0.13

 Gram

-0.13

POSITIVE LOGITS

illion

0.15

steel

0.14

 excit

0.14

ahren

0.14

\e

0.13

 leider

0.13

umba

0.13

pheric

0.13

tring

0.13

Activations Density 0.012%

references to specific months and date-related information

No Comments

No Known Activations