INDEX

Explanations

phrases related to change and adjustment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

erate

-0.18

oin

-0.17

hit

-0.17

æĹ¶åĢĻ

-0.17

ãģĦãĤĭ

-0.17

eled

-0.16

er

-0.16

lie

-0.15

epar

-0.15

hips

-0.15

POSITIVE LOGITS

ers

0.23

 sands

0.22

sburgh

0.21

shape

0.19

iness

0.19

 away

0.18

swith

0.18

gear

0.18

 gears

0.17

Activations Density 0.028%

phrases related to change and adjustment

No Comments

No Known Activations