INDEX

Explanations

numerical values and their organization within text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Campos

-0.15

raphics

-0.14

istol

-0.14

Ð¾Ð·Ð²

-0.14

locator

-0.14

ector

-0.13

fm

-0.13

uz

-0.13

xFE

-0.13

 Mutual

-0.13

POSITIVE LOGITS

ftime

0.16

ìĹħ

0.16

éŁ¿

0.15

ä»Ķ

0.15

LEAN

0.15

asaki

0.14

Fro

0.14

etooth

0.14

 Mand

0.14

ITTE

0.14

Activations Density 0.004%

numerical values and their organization within text

No Comments

No Known Activations