INDEX

Explanations

references to templates in coding or programming contexts

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

Ã´n

-0.17

Ð¾Ð½ÑĮ

-0.15

ascade

-0.14

/loader

-0.14

insk

-0.14

atever

-0.14

ibo

-0.14

embr

-0.14

æ³³

-0.13

heading

-0.13

POSITIVE LOGITS

 GOODMAN

0.20

.foreach

0.15

pecies

0.15

ound

0.15

alto

0.14

erras

0.14

\$

0.14

 Ð¶Ðµ

0.14

Activations Density 0.001%

references to templates in coding or programming contexts

No Comments

No Known Activations