INDEX

Explanations

references to academic journals and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

xl

-0.16

umph

-0.15

UDO

-0.15

zin

-0.15

 Landing

-0.13

 Bloss

-0.13

ÑĢÐ°ÑĤ

-0.13

ude

-0.13

 Sund

-0.13

POSITIVE LOGITS

ĥ

0.16

Ð°ÑĢÑĩ

0.16

ejs

0.16

/gin

0.15

é¸¡

0.15

blk

0.15

 peer

0.14

orean

0.14

slu

0.14

åºĦ

0.14

Activations Density 0.037%

references to academic journals and publications

No Comments

No Known Activations