INDEX

Explanations

references to time-related concepts or parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Pon

-0.15

mainwindow

-0.15

asic

-0.15

itorio

-0.14

\<^

-0.14

omo

-0.14

Ã¼

-0.13

Ãłm

-0.13

oly

-0.13

 Harr

-0.13

POSITIVE LOGITS

otland

0.21

ebin

0.16

 level

0.16

à¸¥à¸°

0.15

cassert

0.14

ensor

0.14

 ÑĥÑĢÐ¾Ð²Ð½Ðµ

0.14

å¤§åħ¨

0.14

cape

0.14

mousedown

0.14

Activations Density 0.387%

references to time-related concepts or parameters

No Comments

No Known Activations