INDEX

Explanations

references to responsibility and accountability in information or agreements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

endon

-0.17

orns

-0.14

okies

-0.14

ouch

-0.14

atik

-0.14

isu

-0.14

 Olson

-0.13

 Dann

-0.13

inery

-0.13

 eldre

-0.13

POSITIVE LOGITS

Ã¼k

0.17

0.16

à¸ģà¸³

0.15

.cgi

0.15

antage

0.14

imd

0.14

ÎµÏĢ

0.14

isen

0.14

avern

0.14

enko

0.14

Activations Density 0.042%

references to responsibility and accountability in information or agreements

No Comments

No Known Activations