INDEX

Explanations

references to time periods or historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

çµĦ

-0.16

-0.14

chg

-0.14

imd

-0.14

æĽ

-0.14

ãĥ£

-0.14

 Stim

-0.14

ior

-0.13

vider

-0.13

oca

-0.13

POSITIVE LOGITS

 part

0.28

 stages

0.23

 portion

0.21

 ÑĩÐ°ÑģÑĤÐ¸

0.18

 parts

0.17

 portions

0.16

 months

0.16

 Î¼ÎŃÏģÎ¿ÏĤ

0.16

 hours

0.16

 ÑĩÐ°ÑģÑĤÑĮ

0.15

Activations Density 0.016%

references to time periods or historical contexts

No Comments

No Known Activations