INDEX

Explanations

references to formal processes or regulations involving permissions and approvals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Zucker

-0.16

orton

-0.15

etag

-0.15

rif

-0.14

 cushion

-0.14

.SC

-0.13

deb

-0.13

Dub

-0.13

 ether

-0.13

izard

-0.13

POSITIVE LOGITS

 Coverage

0.19

 coverage

0.16

Coverage

0.16

essler

0.15

éĳ

0.15

auf

0.15

ihan

0.14

.tencent

0.14

ikan

0.14

breadcrumbs

0.14

Activations Density 0.003%

references to formal processes or regulations involving permissions and approvals

No Comments

No Known Activations