INDEX

Explanations

conjunctions and interrogative phrases related to inquiries or questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ute

-0.17

abar

-0.15

ood

-0.15

ulative

-0.14

oola

-0.14

RequestMethod

-0.14

stderr

-0.14

CLK

-0.14

 trom

-0.14

oute

-0.13

POSITIVE LOGITS

 whom

0.23

Wh

0.20

ellan

0.17

ifs

0.17

 ÚĨÚ¯ÙĪÙĨÙĩ

0.17

Wh

0.17

apesh

0.16

wh

0.16

bow

0.15

ifs

0.15

Activations Density 0.020%

conjunctions and interrogative phrases related to inquiries or questions

No Comments

No Known Activations