INDEX

Explanations

terms related to data handling and processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 Nationals

-0.15

$MESS

-0.14

Obr

-0.13

ÙıÙĪØ§

-0.13

Ð²Ð°Ð´

-0.13

ÐµÑĪ

-0.12

Ð»Ð¾Ð¼

-0.12

ÑĪÐ¸Ð½

-0.12

-:

-0.12

.UInt

-0.12

POSITIVE LOGITS

onet

0.14

Į¨

0.14

pling

0.13

/../

0.13

yx

0.13

 DÃ¼n

0.13

ÃŃnÄĽ

0.13

 consect

0.13

kara

0.13

zimmer

0.13

Activations Density 0.032%

terms related to data handling and processing

No Comments

No Known Activations