INDEX

Explanations

key concepts and challenges in neural network research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

é¡

-0.17

usz

-0.17

chos

-0.15

calcul

-0.14

pletion

-0.14

 calculations

-0.14

uche

-0.14

 Util

-0.14

 Partner

-0.13

 ÏĢÎ±

-0.13

POSITIVE LOGITS

 princip

0.21

 research

0.16

 hardness

0.15

 TRADE

0.15

 knobs

0.15

GAN

0.15

emp

0.15

 bake

0.15

çłĶç©¶

0.15

Activations Density 0.062%

key concepts and challenges in neural network research

No Comments

No Known Activations