INDEX

Explanations

phrases related to implicit meanings and suggestions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

iales

-0.17

ç®¡

-0.15

rum

-0.15

æĿ

-0.15

ãĤ¤ãĥī

-0.15

ç¥¥

-0.15

VERR

-0.14

erras

-0.14

Prince

-0.14

Ð¼ÐµÐ½Ð°

-0.14

POSITIVE LOGITS

_Ptr

0.14

dri

0.14

 indirectly

0.13

 dust

0.13

 packed

0.13

ql

0.13

 wards

0.13

Activations Density 0.171%

phrases related to implicit meanings and suggestions

No Comments

No Known Activations