INDEX

Explanations

phrases indicating achievement or milestones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

eka

-0.19

ê¹

-0.15

istan

-0.15

amus

-0.14

chein

-0.14

ajes

-0.14

izzer

-0.14

Ø¦Ø©

-0.14

ateur

-0.14

ÑĥÑī

-0.13

POSITIVE LOGITS

ilha

0.15

Ø§Ø°

0.14

cname

0.14

iones

0.14

ncy

0.14

rchive

0.14

KeyValue

0.13

 Crystal

0.13

utow

0.13

PN

0.13

Activations Density 0.051%

phrases indicating achievement or milestones

No Comments

No Known Activations