INDEX

Explanations

phrases that express positive news or developments

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

:animated

-0.14

oine

-0.14

 CONTR

-0.14

 ########.

-0.13

top

-0.13

à¤Ŀ

-0.13

çĲĥ

-0.13

:^

-0.13

Ð°Ð¼Ð¿

-0.13

POSITIVE LOGITS

reste

0.18

inta

0.17

¼

0.17

sher

0.16

loat

0.15

 Herm

0.14

submitted

0.14

eus

0.14

ebra

0.14

Paz

0.14

Activations Density 0.013%

phrases that express positive news or developments

No Comments

No Known Activations