INDEX

Explanations

references to digital platforms and media channels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

anga

-0.17

enor

-0.15

 Welt

-0.15

.instant

-0.14

vej

-0.14

 Hakk

-0.14

AYOUT

-0.14

Ð±Ð¸Ð½

-0.13

 kred

-0.13

onga

-0.13

POSITIVE LOGITS

uto

0.15

ivr

0.15

riet

0.14

 currentTime

0.14

zv

0.13

hog

0.13

ëıĮ

0.13

agnet

0.13

 precondition

0.13

Activations Density 0.013%

references to digital platforms and media channels

No Comments

No Known Activations