INDEX

Explanations

brackets and their context within the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

aliyet

-0.17

ishments

-0.17

ktion

-0.16

veloper

-0.16

ishment

-0.15

istrovstvÃŃ

-0.15

peÄį

-0.15

undler

-0.15

zym

-0.14

oins

-0.14

POSITIVE LOGITS

0.15

MD

0.14

Qualifier

0.14

 flushed

0.14

stro

0.14

banner

0.14

oda

0.14

design

0.13

alt

0.13

Activations Density 0.058%

brackets and their context within the text

No Comments

No Known Activations