INDEX

Explanations

ellipses or trailing punctuation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ÐµÐ»Ñİ

-0.17

amba

-0.17

celed

-0.16

oldem

-0.16

quete

-0.15

burger

-0.14

MAND

-0.14

Cad

-0.14

itzer

-0.14

áº£nh

-0.14

POSITIVE LOGITS

eni

0.16

ien

0.16

ah

0.14

 Blessed

0.14

Web

0.14

recht

0.14

rosse

0.14

æ£

0.14

Way

0.14

Activations Density 0.038%

ellipses or trailing punctuation

No Comments

No Known Activations