INDEX

Explanations

numerical and identifier data, particularly dates and specific brands or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

orners

-0.21

lio

-0.17

 Knock

-0.15

iÃŃ

-0.15

aleb

-0.15

amework

-0.15

 jadx

-0.15

iele

-0.15

 synth

-0.15

ghest

-0.15

POSITIVE LOGITS

tone

0.15

lit

0.15

able

0.15

ote

0.15

eca

0.14

lastic

0.14

 íĽ

0.14

ROTO

0.14

ecs

0.14

tty

0.13

Activations Density 0.616%

numerical and identifier data, particularly dates and specific brands or products

No Comments

No Known Activations