INDEX

Explanations

instances of the word "of"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

èķ

-0.16

licate

-0.16

lest

-0.15

.ta

-0.15

_destroy

-0.15

iances

-0.15

ije

-0.15

/*!

-0.14

Ã©lÃ©

-0.14

lements

-0.14

POSITIVE LOGITS

 service

0.16

resources

0.16

rel

0.15

zig

0.15

hon

0.14

service

0.14

aises

0.14

askell

0.14

wig

0.14

res

0.13

Activations Density 0.011%

instances of the word "of"

No Comments

No Known Activations