INDEX

Explanations

discussions about progress, improvement, and the ongoing search for understanding or solutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

imon

-0.15

Ð¾Ð½Ð¾Ð²

-0.14

ÑĩÐ¸

-0.14

.apps

-0.14

Ð¸Ñī

-0.14

-0.13

Scalars

-0.13

ivo

-0.13

ved

-0.13

é¸

-0.13

POSITIVE LOGITS

æ¼«

0.15

.dy

0.15

isclosed

0.14

 Nile

0.14

 WikiLeaks

0.14

AccessType

0.14

à¤¯à¤¨

0.14

ÐĬ

0.14

qli

0.14

endTime

0.13

Activations Density 0.050%

discussions about progress, improvement, and the ongoing search for understanding or solutions

No Comments

No Known Activations