INDEX

Explanations

references to loss and its consequences

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

.Slf

-0.16

lah

-0.15

tle

-0.15

vetica

-0.15

ilent

-0.14

xies

-0.14

lian

-0.14

 fuse

-0.14

Utt

-0.14

shint

-0.14

POSITIVE LOGITS

æİī

0.17

 losses

0.17

á»ĳn

0.16

azzi

0.15

ÐµÐ½Ð¸

0.14

 lost

0.14

Lost

0.13

due

0.13

ÙĬØ¹

0.13

 loss

0.13

Activations Density 0.128%

references to loss and its consequences

No Comments

No Known Activations