INDEX

Explanations

terminology related to connectivity and connection

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

iyat

-0.16

ongan

-0.16

 waived

-0.15

odal

-0.14

amil

-0.14

ÏģÎ¹Î½

-0.14

onal

-0.14

zeug

-0.14

asn

-0.13

asel

-0.13

POSITIVE LOGITS

0.16

stantiate

0.15

ness

0.15

tps

0.15

 ØµÙĨ

0.14

abi

0.14

appa

0.14

etting

0.14

Activations Density 0.008%

terminology related to connectivity and connection

No Comments

No Known Activations