INDEX

Explanations

time-related information and event details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ÙģÙĪ

-0.16

lop

-0.16

earing

-0.15

_Update

-0.14

ktop

-0.14

 ÑģÐ¾Ð±

-0.14

 settlements

-0.13

 ration

-0.13

 index

-0.13

vid

-0.13

POSITIVE LOGITS

 event

0.23

 Event

0.23

/event

0.23

Occurs

0.22

 recurring

0.21

event

0.20

 EVENT

0.20

-event

0.20

.event

0.20

 evento

0.19

Activations Density 0.120%

time-related information and event details

No Comments

No Known Activations