INDEX

Explanations

numerical data or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ãĥ¼ãĥĢ

-0.18

ãĤīãģĦ

-0.17

erne

-0.14

ABCDEFGHIJKLMNOP

-0.14

ozÃŃ

-0.13

iet

-0.13

redicate

-0.13

oad

-0.13

 Goldman

-0.13

erin

-0.13

POSITIVE LOGITS

vise

0.17

bing

0.16

aptor

0.15

thing

0.14

upal

0.14

verity

0.14

AQ

0.13

importe

0.13

berry

0.13

otlin

0.13

Activations Density 0.136%

numerical data or quantities

No Comments

No Known Activations