INDEX

Explanations

mathematical expressions and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

{%

-0.16

iena

-0.15

dio

-0.15

 ÎłÎ»Î·

-0.15

{@

-0.15

anford

-0.14

gio

-0.14

 grunt

-0.14

ostel

-0.14

IFA

-0.14

POSITIVE LOGITS

til

0.17

argin

0.17

Ø§Ø¡

0.16

 prim

0.15

.scalablytyped

0.15

ãĢĩ

0.14

/**↵↵

0.14

arge

0.14

acak

0.13

Activations Density 0.222%

mathematical expressions and structures

No Comments

No Known Activations