INDEX

Explanations

variations of the word "derivative."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

aires

-0.15

Attrib

-0.15

aire

-0.15

antry

-0.14

å·

-0.14

attery

-0.14

ëģĶ

-0.14

ville

-0.14

tree

-0.13

getter

-0.13

POSITIVE LOGITS

uling

0.18

rien

0.17

ungs

0.15

ostream

0.15

ipse

0.14

olvers

0.14

edar

0.14

.BackgroundImageLayout

0.14

aso

0.14

ecycle

0.14

Activations Density 0.015%

variations of the word "derivative."

No Comments

No Known Activations