INDEX

Explanations

words related to defining or outlining specifications and requirements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

swick

-0.16

eras

-0.16

stead

-0.15

age

-0.15

Ã©k

-0.15

olicit

-0.15

usted

-0.15

rette

-0.14

Ã©li

-0.14

maid

-0.14

POSITIVE LOGITS

quential

0.16

ãĥ³ãĥĳ

0.16

roud

0.15

och

0.14

/design

0.14

ãĥ¥

0.14

tember

0.13

venth

0.13

imen

0.13

lÄ±

0.13

Activations Density 0.024%

words related to defining or outlining specifications and requirements

No Comments

No Known Activations