INDEX

Explanations

measurements and dimensions related to products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Cul

-0.19

afia

-0.16

alendar

-0.15

ulton

-0.15

kt

-0.15

Dud

-0.14

mile

-0.14

.xr

-0.14

_CONTROLLER

-0.14

nock

-0.14

POSITIVE LOGITS

cm

0.68

cm

0.63

 cent

0.56

CM

0.54

cms

0.50

CM

0.50

.cm

0.49

(cm

0.47

cms

0.46

_cm

0.46

Activations Density 0.032%

measurements and dimensions related to products

No Comments

No Known Activations