INDEX

Explanations

references to related works and sections in academic formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

hl

-0.15

iddi

-0.14

iffin

-0.14

overy

-0.13

rowad

-0.13

Ø±Ø¯

-0.13

Ð¼Ð¸Ð½Ð¸ÑģÑĤÑĢÐ°

-0.13

ixa

-0.13

rier

-0.13

Terminate

-0.13

POSITIVE LOGITS

vida

0.14

ëĦ·

0.14

 Hers

0.14

UIViewController

0.14

aci

0.14

áº¬

0.13

kaz

0.13

 Interr

0.13

Ð»ÑĸÐ´

0.13

 bent

0.13

Activations Density 0.024%

references to related works and sections in academic formatting

No Comments

No Known Activations