INDEX

Explanations

pronouns related to individuals, particularly focusing on possessive pronouns

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

odash

-0.17

Æ°

-0.17

igans

-0.15

deen

-0.15

 tread

-0.15

Ø§ÛĮØ±

-0.15

uld

-0.14

 Independent

-0.14

 à¤Ĩà¤§

-0.14

ÐµÐ»Ðµ

-0.13

POSITIVE LOGITS

inton

0.16

arrass

0.15

iting

0.14

	Copyright

0.14

igits

0.14

Ãłnh

0.14

imators

0.14

 Ø¹Ø±Ø¨

0.13

 ADVISED

0.13

Activations Density 0.116%

pronouns related to individuals, particularly focusing on possessive pronouns

No Comments

No Known Activations