INDEX

Explanations

words and phrases related to collectibles or memorabilia

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

ARA

-0.16

go

-0.16

.bs

-0.15

worth

-0.15

oj

-0.14

lane

-0.14

erez

-0.14

utive

-0.14

king

-0.14

UME

-0.13

POSITIVE LOGITS

esan

0.17

éŀ

0.16

ycl

0.15

pek

0.14

pees

0.14

 share

0.14

Äįan

0.14

 ferr

0.14

Å¾e

0.14

issen

0.14

Activations Density 0.000%

words and phrases related to collectibles or memorabilia

No Comments

No Known Activations