INDEX

Explanations

the word "only" and its variations

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

lez

-0.17

èĩ³å°ĳ

-0.16

 atleast

-0.16

irty

-0.15

 least

-0.15

lej

-0.15

ajo

-0.14

rame

-0.14

anka

-0.14

Nin

-0.14

POSITIVE LOGITS

 handful

0.25

few

0.21

 partial

0.20

 partially

0.19

one

0.18

 recently

0.17

 Partial

0.17

two

0.17

 limited

0.16

 fraction

0.16

Activations Density 0.078%

the word "only" and its variations

No Comments

No Known Activations