INDEX

Explanations

questions about specific topics or concerns

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olist

-0.16

uttle

-0.15

rah

-0.15

ÑĢÐ¾Ð²Ð¸Ñĩ

-0.14

ostringstream

-0.14

pping

-0.14

ãĤ¯ãĥĪ

-0.14

ibia

-0.14

ewater

-0.13

alom

-0.13

POSITIVE LOGITS

 intern

0.16

ares

0.15

%#

0.15

éĤ£äºĽ

0.15

/Library

0.14

 ná»¯a

0.14

beck

0.14

.utf

0.14

taÅŁ

0.14

 Intern

0.14

Activations Density 0.028%

questions about specific topics or concerns

No Comments

No Known Activations