INDEX

Explanations

dates and times in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

maj

-0.17

ÎµÏģÎ¹

-0.16

 Frankie

-0.15

ÑĤÑı

-0.15

exp

-0.14

igar

-0.14

pip

-0.14

erp

-0.13

 trunk

-0.13

 then

-0.13

POSITIVE LOGITS

icast

0.18

eyer

0.17

Î´ÏģÎ¿

0.16

ochen

0.15

ipt

0.15

Å¾el

0.15

ekk

0.14

ë³¼

0.14

Activations Density 0.063%

dates and times in the text

No Comments

No Known Activations