INDEX

Explanations

frequent punctuation marks, particularly periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

-0.20

-0.19

...

-0.18

Furthermore

-0.18

it

-0.17

ï¿½

-0.17

Additionally

-0.17

POSITIVE LOGITS

ORG

0.24

Us

0.17

itoris

0.17

 addCriterion

0.17

UsageId

0.17

ÙĥÙĪÙħ

0.16

@student

0.16

illegal

0.15

ystore

0.15

etc

0.15

Activations Density 1.053%

frequent punctuation marks, particularly periods

No Comments

No Known Activations