INDEX

Explanations

technical terms and concepts related to neural networks and artificial intelligence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

tin

-0.15

eron

-0.14

iev

-0.13

izo

-0.13

abbo

-0.13

Ð¾Ð·Ñı

-0.13

[][]

-0.13

aton

-0.13

ulos

-0.13

entry

-0.13

POSITIVE LOGITS

.scalablytyped

0.16

ëĭ´

0.14

unts

0.14

NonNull

0.13

alm

0.13

alytics

0.13

builtin

0.13

Ð·Ð½Ð°ÑĩÐ°

0.13

asant

0.13

ÑģÑĮÐ¾Ð³Ð¾

0.13

Activations Density 0.005%

technical terms and concepts related to neural networks and artificial intelligence

No Comments

No Known Activations