INDEX

Explanations

references to the structure and hierarchy of child elements in a component tree

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ccione

-0.17

Å¡ov

-0.16

rete

-0.16

eer

-0.15

unden

-0.15

bjerg

-0.14

iaux

-0.14

ichick

-0.14

yect

-0.14

POSITIVE LOGITS

aney

0.16

 Bale

0.15

-most

0.15

 Grimm

0.14

/root

0.14

ust

0.14

Lud

0.14

/original

0.14

 Loren

0.13

ãĥ¬ãĥĥãĥĪ

0.13

Activations Density 0.047%

references to the structure and hierarchy of child elements in a component tree

No Comments

No Known Activations