INDEX

Explanations

phrases indicating potential or capability 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 @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

undi

-0.15

chner

-0.15

Nonce

-0.15

inia

-0.14

.isPresent

-0.14

bud

-0.14

ÑĥÐ¶

-0.14

ledon

-0.14

olia

-0.14

CEE

-0.14

POSITIVE LOGITS

 Carrier

0.18

Carrier

0.17

imbus

0.17

 carrier

0.16

jak

0.15

ockey

0.14

hist

0.14

ilon

0.14

RSS

0.14

Ã¥n

0.14

Activations Density 0.143%

phrases indicating potential or capability in various contexts

No Comments

No Known Activations