INDEX

Explanations

references to specific years, particularly in the context of dates and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ings

-0.16

och

-0.16

hetto

-0.15

pip

-0.14

ÏĢÎŃ

-0.14

rypton

-0.14

erm

-0.14

 others

-0.13

 Gros

-0.13

itter

-0.13

POSITIVE LOGITS

jourd

0.17

Ã±as

0.15

ught

0.15

yms

0.15

iÃ¨me

0.14

Ø©

0.14

gether

0.14

-Za

0.14

 Ð´Ð¾ÑĤ

0.14

ilight

0.13

Activations Density 0.051%

references to specific years, particularly in the context of dates and events

No Comments

No Known Activations