INDEX

Explanations

phrases indicating instruction or advice

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

 cherry

-0.15

REFERRED

-0.14

chg

-0.14

gems

-0.13

 Leban

-0.13

 meaning

-0.13

.setViewport

-0.13

.Compose

-0.13

 Hicks

-0.13

 become

-0.13

POSITIVE LOGITS

 prevent

0.20

 Prevent

0.19

 achie

0.17

 achieving

0.17

 achieved

0.17

 achieve

0.17

Achie

0.17

 prevents

0.17

prevent

0.17

 created

0.17

Activations Density 0.115%

phrases indicating instruction or advice

No Comments

No Known Activations