INDEX

Explanations

specific measurements and dimensions associated with books or artwork

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

orgh

-0.21

urr

-0.17

PEND

-0.15

Ãºi

-0.15

Ped

-0.14

ut

-0.14

andra

-0.14

 Elastic

-0.14

ull

-0.13

 elastic

-0.13

POSITIVE LOGITS

Mahon

0.15

.LayoutStyle

0.15

onus

0.14

Å¡ku

0.14

jeta

0.14

enso

0.14

#ac

0.14

å©·

0.14

ERO

0.14

ØŃØ§Ø¯

0.14

Activations Density 0.025%

specific measurements and dimensions associated with books or artwork

No Comments

No Known Activations