INDEX

Explanations

references to significant dates and view counts in media contexts

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

oldem

-0.19

buster

-0.14

nob

-0.14

 sign

-0.14

Ì£

-0.14

ÐµÑĢÑĪ

-0.14

rats

-0.14

 ÙĤØ±

-0.13

resenter

-0.13

exist

-0.13

POSITIVE LOGITS

oint

0.15

 Uncategorized

0.15

anel

0.14

å¤®

0.14

Lon

0.14

awn

0.14

 ÐĿÐ°ÑģÐµÐ»ÐµÐ½Ð¸Ðµ

0.14

å¼¾

0.14

/Math

0.14

å¼¹

0.14

Activations Density 0.023%

references to significant dates and view counts in media contexts

No Comments

No Known Activations