INDEX

Explanations

references to specific decades or historical periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

urette

-0.21

utut

-0.19

 HÃ¼s

-0.18

 Truy

-0.16

ony

-0.14

specifier

-0.14

preload

-0.14

Updated

-0.14

aversable

-0.14

vetica

-0.14

POSITIVE LOGITS

0.25

å¹´ä»£

0.19

0.17

adm

0.16

ukes

0.15

era

0.15

ies

0.15

erais

0.15

ures

0.14

ItemClickListener

0.14

Activations Density 0.023%

references to specific decades or historical periods

No Comments

No Known Activations