INDEX

Explanations

instances of the word "on" 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 @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 habil

-0.16

kl

-0.16

 Bliss

-0.15

ilter

-0.15

ITTE

-0.14

itte

-0.14

 Neue

-0.14

 Miner

-0.14

ijk

-0.14

empo

-0.14

POSITIVE LOGITS

ãĥ³ãĥĲ

0.19

è¦ª

0.16

/vendors

0.15

ÑĢÐ¸Ð¿

0.15

ÃĬ

0.14

Ð¾Ð»Ð¶

0.14

Ð½Ð¸Ð·

0.14

ÑĪÐºÐ¸

0.14

ipar

0.14

é½Ĳ

0.14

Activations Density 0.125%

instances of the word "on" in various contexts

No Comments

No Known Activations