INDEX

Explanations

terms related to job positions and industry classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 dilig

-0.15

ugas

-0.15

oni

-0.14

isse

-0.14

.sess

-0.14

.dp

-0.14

uda

-0.13

 Corinth

-0.13

icle

-0.13

opol

-0.13

POSITIVE LOGITS

/apis

0.17

nes

0.17

 clocks

0.17

Hoa

0.16

_misc

0.15

/misc

0.15

Misc

0.14

elsen

0.14

arkin

0.14

misc

0.14

Activations Density 0.170%

terms related to job positions and industry classifications

No Comments

No Known Activations