INDEX

Explanations

programming-related keywords and syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

lander

-0.18

ote

-0.15

ow

-0.15

Ð»Ð¾Ð¹

-0.15

loy

-0.15

Kob

-0.14

 Vanessa

-0.14

å·¦åı³

-0.14

oi

-0.14

POSITIVE LOGITS

ÐĲÑĢÑħÑĸÐ²

0.16

ÐµÑĢÐ²

0.15

_marshall

0.15

ÑģÑĤÐ²Ð¾ÑĢ

0.15

ãģķãģĦ

0.15

ascus

0.15

Ð±Ð°Ñĩ

0.14

ÐĶÐļ

0.14

.requireNonNull

0.14

 RESP

0.14

Activations Density 0.003%

programming-related keywords and syntax

No Comments

No Known Activations