INDEX

Explanations

phrases indicating relationships or comparisons between entities

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

ÐµÑĢÑĪ

-0.16

ãģĻãģİ

-0.15

loi

-0.15

ÐºÐ°ÑĢ

-0.15

vern

-0.15

earer

-0.15

orbit

-0.15

imon

-0.15

ahan

-0.15

Dic

-0.14

POSITIVE LOGITS

kenin

0.17

iesz

0.14

 erect

0.14

eto

0.14

aptop

0.14

depending

0.13

 patterns

0.13

Apt

0.13

Aid

0.13

mage

0.13

Activations Density 0.246%

phrases indicating relationships or comparisons between entities

No Comments

No Known Activations