INDEX

Explanations

numerical data, particularly statistics and significant figures within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ades

-0.15

Ø§Ø´Øª

-0.14

è¾¾

-0.14

icaret

-0.14

peq

-0.14

meler

-0.14

/thread

-0.14

IDI

-0.13

CTYPE

-0.13

axes

-0.13

POSITIVE LOGITS

th

0.44

th

0.37

thin

0.29

_th

0.28

Th

0.27

á

0.27

TH

0.25

thon

0.25

oth

0.25

(th

0.23

Activations Density 0.043%

numerical data, particularly statistics and significant figures within the text

No Comments

No Known Activations