INDEX

Explanations

conditional statements and instructions related to programming or coding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

itter

-0.15

rove

-0.15

osemite

-0.14

avou

-0.14

estre

-0.14

locator

-0.14

asl

-0.14

ellido

-0.14

kit

-0.13

POSITIVE LOGITS

Ìĥ

0.15

ÑĪÐºÐ¸

0.14

orian

0.14

åŃ¦éĻ¢

0.14

 resumed

0.14

 Grey

0.14

 resume

0.14

 Resume

0.13

lao

0.13

alan

0.13

Activations Density 0.002%

conditional statements and instructions related to programming or coding

No Comments

No Known Activations