INDEX

Explanations

instances of observance or documentation of events or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

URY

-0.17

-0.16

ury

-0.15

of

-0.14

oose

-0.14

agh

-0.14

erk

-0.14

gh

-0.14

Ã¤l

-0.14

POSITIVE LOGITS

 worden

0.23

izzato

0.20

.nlm

0.18

 werden

0.17

 à¤Ĺà¤¯

0.17

 zosta

0.17

rena

0.17

 getting

0.16

 Getting

0.16

 wordt

0.15

Activations Density 0.016%

instances of observance or documentation of events or conditions

No Comments

No Known Activations