INDEX

Explanations

instances of clickable links and buttons in the text

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

uch

-0.16

haven

-0.16

-de

-0.15

Dud

-0.15

 loving

-0.14

istan

-0.14

/welcome

-0.14

ÙĨØ¯Ùĩ

-0.14

KP

-0.14

bon

-0.14

POSITIVE LOGITS

nonnull

0.17

ryfall

0.16

wdx

0.16

ìļ°ë¦¬

0.14

Ð¹ÑĤÐµ

0.14

eydi

0.14

 registrazione

0.14

çĤī

0.14

¶Į

0.14

;element

0.13

Activations Density 0.028%

instances of clickable links and buttons in the text

No Comments

No Known Activations