INDEX

Explanations

instances of the pronoun "it" and related phrases indicating actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

à¸´à¸į

-0.15

Ø±Ø¯Ùĩ

-0.15

Äı

-0.15

 cena

-0.14

uebas

-0.14

WISE

-0.14

Î¯ÏīÎ½

-0.13

vailability

-0.13

otros

-0.13

 jadx

-0.13

POSITIVE LOGITS

 emerged

0.20

 trans

0.19

 appears

0.18

 follows

0.18

 Emerging

0.17

Emer

0.17

 emerge

0.17

 ÑģÐ»ÐµÐ´ÑĥÐµÑĤ

0.17

 Emer

0.17

was

0.16

Activations Density 0.074%

instances of the pronoun "it" and related phrases indicating actions or states

No Comments

No Known Activations