INDEX

Explanations

phrases related to observation and inquiry about events or outcomes

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

zes

-0.16

 guarantee

-0.15

aller

-0.14

lesia

-0.14

oven

-0.14

zug

-0.13

ab

-0.13

ÏģÎ³

-0.13

udes

-0.13

zy

-0.13

POSITIVE LOGITS

RIES

0.18

ries

0.18

ìłĢ

0.17

elle

0.16

ãĥ¼ãĤ¹

0.15

ewe

0.14

EditMode

0.14

Ã¶yle

0.14

 ìĿµ

0.14

Utf

0.14

Activations Density 0.076%

phrases related to observation and inquiry about events or outcomes

No Comments

No Known Activations