INDEX

Explanations

instances of the word "think."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 doesn

-0.17

 whom

-0.16

ä¸įè¦ģ

-0.16

 Doesn

-0.16

 Ð½Ðµ

-0.15

 doesnt

-0.15

 khÃ´ng

-0.15

asÄ±yla

-0.15

 nicht

-0.15

NOT

-0.15

POSITIVE LOGITS

/h

0.17

 maybe

0.16

ered

0.15

IALIZED

0.15

 perhaps

0.15

it

0.14

maybe

0.13

/goto

0.13

anch

0.13

 they

0.13

Activations Density 0.047%

instances of the word "think."

No Comments

No Known Activations