INDEX

Explanations

numerical information and references within the 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

olle

-0.15

 Amen

-0.14

oot

-0.13

ãĥ¼ãĥ©

-0.13

ANNER

-0.13

POSITIVE LOGITS

zelf

0.17

alta

0.15

untu

0.15

intree

0.15

anzeigen

0.15

idia

0.14

 Laud

0.14

TestingModule

0.14

rts

0.13

oop

0.13

Activations Density 0.119%

numerical information and references within the text

No Comments

No Known Activations