INDEX

Explanations

terms related to specialization and expertise in various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

age

-0.19

ning

-0.17

atha

-0.15

udu

-0.14

/check

-0.14

 swell

-0.14

ucc

-0.14

åĴ²

-0.14

rior

-0.14

 Hawk

-0.14

POSITIVE LOGITS

/general

0.19

à¹Ģà¸īà¸ŀà¸²à¸°

0.17

 ë¶Ħìķ¼

0.17

-purpose

0.17

 biá»ĩt

0.15

ìłĲ

0.15

/target

0.15

-instance

0.15

itag

0.15

sed

0.15

Activations Density 0.015%

terms related to specialization and expertise in various fields

No Comments

No Known Activations