INDEX

Explanations

references to devices and their functionality

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

ftime

-0.16

glich

-0.16

 Elias

-0.14

umont

-0.14

hammer

-0.14

tn

-0.14

owie

-0.14

CompleteListener

-0.14

Cly

-0.14

 Employer

-0.14

POSITIVE LOGITS

imals

0.17

andle

0.17

ablo

0.15

olland

0.15

abant

0.15

orial

0.14

 proper

0.14

ìĹŃ

0.14

zag

0.14

icago

0.14

Activations Density 0.015%

references to devices and their functionality

No Comments

No Known Activations