INDEX

Explanations

the word "that" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ãģĤãģ£ãģŁ

-0.20

ãģĤãĤĭ

-0.19

Ùĩ

-0.18

amp

-0.17

iously

-0.17

ãģĬ

-0.16

 them

-0.16

ãģĤãĤĬ

-0.16

them

-0.16

 Ø§ÛĮÙĨÚ©Ùĩ

-0.16

POSITIVE LOGITS

ched

0.30

 they

0.27

 there

0.26

ching

0.25

there

0.21

 although

0.21

they

0.21

we

0.21

/how

0.20

/if

0.20

Activations Density 0.589%

the word "that" in various contexts

No Comments

No Known Activations