INDEX

Explanations

terms related to organizational roles and job titles within various sectors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

eyse

-0.17

.ibm

-0.16

yntax

-0.16

ompiler

-0.16

Æ¡i

-0.16

Exporter

-0.15

Ð¾Ð´Ñĥ

-0.15

ê±°ëŀĺê°Ģ

-0.15

NameValuePair

-0.15

enÄĽ

-0.14

POSITIVE LOGITS

 matters

0.21

 affairs

0.20

ext

0.19

 division

0.19

 Matters

0.18

äºĭ

0.17

 External

0.17

 Integration

0.17

 external

0.17

 relations

0.16

Activations Density 0.300%

terms related to organizational roles and job titles within various sectors

No Comments

No Known Activations