INDEX

Explanations

the word "or" used 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Äįil

-0.16

ilor

-0.16

-0.15

iled

-0.15

ils

-0.15

ãĥ¥ãĥ¼

-0.14

ãĤĨ

-0.14

imized

-0.14

ilt

-0.14

notated

-0.14

POSITIVE LOGITS

two

0.31

two

0.24

 couple

0.23

-two

0.21

ä¸¤ä¸ª

0.20

 deux

0.20

 zwei

0.20

few

0.20

ä¸¤

0.19

åħ©

0.19

Activations Density 0.022%

the word "or" used in various contexts

No Comments

No Known Activations