INDEX

Explanations

discussions about academic research and methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

spell

-0.14

 spell

-0.14

olon

-0.14

Wid

-0.14

agy

-0.13

occo

-0.13

Spell

-0.13

åĲĽ

-0.13

iverse

-0.13

angler

-0.13

POSITIVE LOGITS

 Petit

0.15

ÐµÑģÑĮ

0.15

 sincer

0.14

èĥ½å¤Ł

0.14

ickness

0.14

peri

0.14

wap

0.14

cope

0.13

Ã¸d

0.13

Activations Density 0.001%

discussions about academic research and methodologies

No Comments

No Known Activations