INDEX

Explanations

references to entities and organizational information, particularly about companies and their financial details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

eyn

-0.15

acho

-0.15

wet

-0.14

Wet

-0.14

 Malk

-0.14

opot

-0.14

uctor

-0.14

spot

-0.13

POSITIVE LOGITS

nement

0.16

Ð½Ð¸Ð·

0.16

olean

0.16

opensource

0.15

omid

0.14

fax

0.14

ÑĢÐ°Ð±Ð¾ÑĤ

0.14

 Baths

0.14

oler

0.13

asser

0.13

Activations Density 0.002%

references to entities and organizational information, particularly about companies and their financial details

No Comments

No Known Activations