INDEX

Explanations

elements of text that suggest a formal or structured writing style

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ezier

-0.17

.scalablytyped

-0.17

ulen

-0.16

?url

-0.15

Convertible

-0.15

ower

-0.15

Î´Î±

-0.15

iddet

-0.15

ernals

-0.14

rient

-0.14

POSITIVE LOGITS

aler

0.17

Lorem

0.16

ALER

0.15

 Lorem

0.15

hol

0.14

Dol

0.14

 hare

0.14

que

0.13

yny

0.13

orer

0.13

Activations Density 0.018%

elements of text that suggest a formal or structured writing style

No Comments

No Known Activations