INDEX

Explanations

abbreviations or acronyms related to specific fields or discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

usch

-0.20

Ð»ÑıÐ½

-0.16

_fsm

-0.15

idian

-0.15

 loose

-0.15

Ð²Ñĥ

-0.15

conv

-0.14

Ð½Ð¸Ð½Ð°

-0.14

Īĺ

-0.14

 States

-0.14

POSITIVE LOGITS

rÅ¾

0.14

.LoggerFactory

0.14

 Confidential

0.14

quared

0.14

æŁ

0.14

urai

0.14

 Cousins

0.14

etrics

0.14

Sle

0.14

Activations Density 0.072%

abbreviations or acronyms related to specific fields or discussions

No Comments

No Known Activations