INDEX

Explanations

references to comparisons between different time periods, particularly regarding social standards and achievements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

erot

-0.17

.flow

-0.16

ucht

-0.16

orgen

-0.16

ëĳ

-0.15

regon

-0.15

ingleton

-0.15

ddit

-0.14

neau

-0.14

uegos

-0.14

POSITIVE LOGITS

era

0.22

 epoch

0.19

Era

0.18

err

0.17

-era

0.16

Err

0.16

Err

0.15

æĺŃåĴĮ

0.15

é¢Ħè§Ī

0.15

era

0.15

Activations Density 0.459%

references to comparisons between different time periods, particularly regarding social standards and achievements

No Comments

No Known Activations