INDEX

Explanations

programming-related syntax and error handling terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

oose

-0.16

ught

-0.16

 Seeder

-0.15

à¥Įà¤¨

-0.14

abis

-0.14

UInteger

-0.13

::__

-0.13

stairs

-0.13

/cms

-0.13

otal

-0.13

POSITIVE LOGITS

 Goodman

0.17

.col

0.16

hev

0.16

é»

0.15

istrovstvÃŃ

0.15

;amp

0.15

REFER

0.15

 GOODMAN

0.14

IEW

0.14

Activations Density 0.004%

programming-related syntax and error handling terms

No Comments

No Known Activations