INDEX

Explanations

instances of the word "or" indicating alternatives or choices

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

ouv

-0.17

 Restr

-0.15

 intra

-0.15

Î»Î¼

-0.15

unsch

-0.14

bred

-0.14

toPromise

-0.14

illes

-0.14

æħĭ

-0.14

urally

-0.14

POSITIVE LOGITS

 Hers

0.21

Her

0.20

Her

0.20

 hers

0.20

her

0.20

ific

0.17

HER

0.17

her

0.16

 herself

0.16

.her

0.16

Activations Density 0.005%

instances of the word "or" indicating alternatives or choices

No Comments

No Known Activations