INDEX

Explanations

instances of the word "that" and its various forms, indicating a focus on explanatory or defining statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

.datas

-0.15

ãĥ«ãĤ¯

-0.15

è¿Ļä¹Ī

-0.15

irsch

-0.14

Ã¤

-0.14

ÑĪÐµÐ²

-0.14

legate

-0.14

imer

-0.14

arpa

-0.14

Ð°Ð»ÐµÐ¶

-0.14

POSITIVE LOGITS

urdu

0.15

ceed

0.15

Ð¾ÑĢÐ¾Ð´

0.14

itel

0.14

0.13

andÄ±r

0.13

ango

0.13

/reset

0.13

 whole

0.13

ohl

0.13

Activations Density 0.077%

instances of the word "that" and its various forms, indicating a focus on explanatory or defining statements

No Comments

No Known Activations