INDEX

Explanations

references to specific time periods and dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

&r

-0.17

orsche

-0.15

canf

-0.15

codegen

-0.14

ãĥ³ãĥĪ

-0.14

hu

-0.13

xfd

-0.13

orem

-0.13

HU

-0.13

izable

-0.13

POSITIVE LOGITS

 same

0.24

same

0.24

 SAME

0.20

Same

0.20

Å¼e

0.19

 mismo

0.19

 stesso

0.18

SAME

0.17

zelf

0.17

 Same

0.17

Activations Density 0.108%

references to specific time periods and dates

No Comments

No Known Activations