INDEX

Explanations

references to structured data and agreements across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

awns

-0.15

ammer

-0.15

utsch

-0.14

ãģĻãģĻ

-0.13

seed

-0.13

kee

-0.13

 Nack

-0.13

tram

-0.13

eec

-0.13

anonymous

-0.13

POSITIVE LOGITS

ubble

0.16

ishly

0.16

.Apis

0.15

æ®Ĭ

0.15

_EMIT

0.15

0.14

doch

0.14

yw

0.14

ãĥ³ãĥĩãĤ£

0.14

_issue

0.14

Activations Density 0.015%

references to structured data and agreements across various contexts

No Comments

No Known Activations