INDEX

Explanations

phrases indicating the initiation or progression of actions and feelings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 continue

-0.23

 continued

-0.22

continue

-0.21

 continuing

-0.21

 continuation

-0.19

 continues

-0.19

	continue

-0.19

continued

-0.18

 still

-0.18

 continuar

-0.17

POSITIVE LOGITS

ying

0.21

 Ð¿Ð¾Ð±Ð°

0.15

 notice

0.15

 serious

0.15

 noticed

0.15

lesh

0.15

 taper

0.15

 seriously

0.15

 NOTICE

0.15

Activations Density 0.035%

phrases indicating the initiation or progression of actions and feelings

No Comments

No Known Activations