INDEX

Explanations

phrases related to singular terminology or individual units

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

Ú¯Ø§Ùĩ

-0.16

sel

-0.16

ãģĬãĤĬ

-0.16

ãģĦãģ¾ãģĻ

-0.15

daq

-0.15

ran

-0.14

adil

-0.14

ÑĢÐ°Ð½

-0.14

sj

-0.13

ses

-0.13

POSITIVE LOGITS

tons

0.27

/single

0.22

 giáº£n

0.19

 baÅŁÄ±na

0.18

-handed

0.17

(single

0.17

pulse

0.17

omas

0.16

ton

0.15

 NotSupportedException

0.15

Activations Density 0.034%

phrases related to singular terminology or individual units

No Comments

No Known Activations