INDEX

Explanations

key numerical values and their context in 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 @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

-0.15

ugo

-0.14

gba

-0.14

adol

-0.14

qb

-0.14

allo

-0.13

contres

-0.13

itten

-0.13

olt

-0.13

POSITIVE LOGITS

 surrounded

0.14

onus

0.14

/includes

0.14

 cref

0.14

 surround

0.13

Po

0.13

gesi

0.13

.cgi

0.13

 ÑĩÐ¸Ñģ

0.13

DW

0.13

Activations Density 0.021%

key numerical values and their context in the text

No Comments

No Known Activations