INDEX

Explanations

actions related to cleaning and organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

lage

-0.16

gt

-0.15

ÑĢÐµÑĪ

-0.15

asty

-0.14

leg

-0.14

ilet

-0.14

tees

-0.14

owo

-0.13

tems

-0.13

Client

-0.13

POSITIVE LOGITS

liness

0.25

.clean

0.18

-cut

0.17

 slate

0.17

mate

0.16

(clean

0.16

 thoroughly

0.15

artz

0.15

 dirty

0.15

est

0.15

Activations Density 0.033%

actions related to cleaning and organization

No Comments

No Known Activations