INDEX

Explanations

references to government officials or ministers

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

(~(

-0.16

lore

-0.16

ainen

-0.15

Fur

-0.15

 stick

-0.14

Ð¾ÑĢÐ¾Ð·

-0.14

ÐµÐ²Ð¸Ñĩ

-0.14

senal

-0.14

orman

-0.13

ç«ĭãģ¦

-0.13

POSITIVE LOGITS

ayed

0.17

inea

0.16

joy

0.15

 SHIPPING

0.15

kÃ³w

0.15

 Shipping

0.14

idon

0.14

riangle

0.14

age

0.14

 objev

0.14

Activations Density 0.017%

references to government officials or ministers

No Comments

No Known Activations