INDEX

Explanations

the verb "be" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

rema

-0.19

èĥ½å¤Ł

-0.16

contre

-0.15

ãĥ³ãĥĳ

-0.15

erie

-0.15

being

-0.15

 Roads

-0.15

utura

-0.15

WARDS

-0.15

æķ¢

-0.15

POSITIVE LOGITS

 easily

0.22

ister

0.19

't

0.19

’t

0.19

 seen

0.18

isters

0.17

ISTER

0.16

 freely

0.15

.Vector

0.15

ena

0.15

Activations Density 0.071%

the verb "be" in various contexts

No Comments

No Known Activations