INDEX

Explanations

concepts related to key themes, benefits, and features in various contexts, especially in terms of organization and planning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

à¸¥à¸°

-0.17

lid

-0.16

 Saud

-0.15

Scoped

-0.14

dea

-0.14

oler

-0.14

tember

-0.14

èĸ¦

-0.14

wo

-0.14

 solicit

-0.13

POSITIVE LOGITS

ä¹ĭä¸Ģ

0.24

 unto

0.19

 sine

0.17

ppe

0.16

 bagi

0.16

 among

0.15

ikt

0.14

 throughout

0.14

Activations Density 0.161%

concepts related to key themes, benefits, and features in various contexts, especially in terms of organization and planning

No Comments

No Known Activations