INDEX

Explanations

forms of the verb "to be."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

holm

-0.18

sg

-0.16

ton

-0.15

ãĥ¼ãĤ

-0.15

itical

-0.14

ãģĵãģ¨ãģ¯

-0.14

my

-0.14

ard

-0.14

gence

-0.14

urd

-0.14

POSITIVE LOGITS

/how

0.23

/is

0.23

/w

0.22

 supposed

0.21

/do

0.16

earch

0.16

sembles

0.16

±Ð¾ÑĤ

0.15

gere

0.15

/goto

0.15

Activations Density 0.114%

forms of the verb "to be."

No Comments

No Known Activations