INDEX

Explanations

descriptive adjectives or phrases that convey quantifiable attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

orf

-0.15

raquo

-0.15

ancellable

-0.15

ãĥ³ãĥĨ

-0.15

loquent

-0.14

okoj

-0.14

Ñĵ

-0.14

zac

-0.14

acket

-0.14

dff

-0.14

POSITIVE LOGITS

-sk

0.35

sk

0.34

Sk

0.34

Sk

0.31

sk

0.30

_sk

0.29

SK

0.26

SK

0.24

.sk

0.24

(sk

0.23

Activations Density 0.033%

descriptive adjectives or phrases that convey quantifiable attributes

No Comments

No Known Activations