INDEX

Explanations

expressions of gratitude and acknowledgment

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

vig

-0.15

ichael

-0.15

-chain

-0.14

uther

-0.14

XT

-0.14

uint

-0.14

enger

-0.13

LOC

-0.13

zsche

-0.13

 Selbst

-0.13

POSITIVE LOGITS

/sbin

0.16

erville

0.15

odal

0.15

uz

0.15

atory

0.14

 Brill

0.14

 Cust

0.14

/welcome

0.14

orrar

0.14

warts

0.14

Activations Density 0.025%

expressions of gratitude and acknowledgment

No Comments

No Known Activations