INDEX

Explanations

references to allegations and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ugs

-0.15

rk

-0.15

.EOF

-0.15

.scalablytyped

-0.15

sson

-0.14

etty

-0.14

rw

-0.14

icles

-0.14

etag

-0.14

oust

-0.14

POSITIVE LOGITS

orical

0.32

iances

0.31

edly

0.29

iance

0.29

ory

0.27

iant

0.24

ations

0.24

ato

0.24

 Alleg

0.22

ret

0.21

Activations Density 0.004%

references to allegations and related terms

No Comments

No Known Activations