INDEX

Explanations

details about historical figures and their roles

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

ÑĢÐ°Ñĩ

-0.18

 sulfur

-0.17

 theater

-0.16

 counselors

-0.15

 forever

-0.15

ä¹¾

-0.15

 Nonetheless

-0.14

 lawmaker

-0.14

uell

-0.14

 Theater

-0.14

POSITIVE LOGITS

 Mess

0.20

 wireless

0.18

Mess

0.18

 portion

0.17

 wired

0.17

 Wireless

0.15

ummies

0.15

 Bros

0.15

 messed

0.15

 alright

0.15

Activations Density 0.084%

details about historical figures and their roles

No Comments

No Known Activations