INDEX

Explanations

instances of the word "that" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ãĤ¢ãĥ«

-0.15

Ð´Ð°Ð¿

-0.14

à¸³

-0.14

itty

-0.14

agt

-0.14

Ø³ÙĬÙĨ

-0.14

reed

-0.13

ux

-0.13

elmet

-0.13

 omas

-0.13

POSITIVE LOGITS

ìķ½

0.15

patial

0.15

iaz

0.14

Î¼Î¿Î½

0.14

.si

0.14

edio

0.14

Byl

0.14

cn

0.14

0.13

Activations Density 0.115%

instances of the word "that" in various contexts

No Comments

No Known Activations