INDEX

Explanations

terms and phrases related to external factors or components that have an influential role

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ê¶ģ

-0.16

á»¥y

-0.15

ansk

-0.15

Å¡ÃŃ

-0.14

berger

-0.14

 retal

-0.14

ÄĻd

-0.14

AGO

-0.14

Ð°ÑĦ

-0.13

æķħ

-0.13

POSITIVE LOGITS

egra

0.15

 empt

0.14

Hem

0.13

ctic

0.13

Bat

0.13

 Surgery

0.13

ä¹ī

0.13

lund

0.13

Activations Density 0.002%

terms and phrases related to external factors or components that have an influential role

No Comments

No Known Activations