INDEX

Explanations

dates and time-related references

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

lap

-0.16

æĪ¸

-0.16

rej

-0.16

Å¥

-0.15

engu

-0.14

lag

-0.14

 thá»ķ

-0.14

chaft

-0.14

ãĥĨãĥ«

-0.14

POSITIVE LOGITS

/TT

0.18

atra

0.15

itom

0.15

omor

0.14

 assignable

0.14

à¸µà¹Ģà¸Ķ

0.14

anches

0.13

Īëĭ¤

0.13

alsa

0.13

ivol

0.13

Activations Density 0.015%

dates and time-related references

No Comments

No Known Activations