INDEX

Explanations

punctuation and formatting elements 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 @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

rganization

-0.17

etty

-0.17

it

-0.16

adel

-0.15

ï¿½

-0.15

iec

-0.15

rzy

-0.15

emit

-0.15

POSITIVE LOGITS

ORG

0.26

 addCriterion

0.17

etc

0.17

UsageId

0.17

ÙĥÙĪÙħ

0.17

etc

0.16

jpg

0.16

inel

0.16

venge

0.15

illegal

0.15

Activations Density 0.446%

punctuation and formatting elements within the text

No Comments

No Known Activations