INDEX

Explanations

phrases indicating reasons or justifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

quette

-0.16

occo

-0.16

iji

-0.15

otti

-0.15

ientos

-0.15

sn

-0.14

aar

-0.14

alles

-0.14

astro

-0.13

encies

-0.13

POSITIVE LOGITS

 DÃ¼n

0.16

ancell

0.15

asive

0.15

hap

0.15

arend

0.14

á»ĭ

0.14

ä¸įåı¯

0.14

 McGr

0.14

oyer

0.14

liÅ¡

0.14

Activations Density 0.028%

phrases indicating reasons or justifications

No Comments

No Known Activations