INDEX

Explanations

terms related to numerical analysis and simulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

oni

-0.17

ooke

-0.14

ahn

-0.13

 Wikip

-0.13

eken

-0.13

 baÅŁÄ±na

-0.13

á»ĳt

-0.13

Ð¾Ð±ÑĢÐ°Ð·

-0.13

PRO

-0.12

 tonight

-0.12

POSITIVE LOGITS

frau

0.15

 Velocity

0.14

ig

0.14

sonian

0.14

 Pick

0.13

 Swinger

0.13

indle

0.13

 Perry

0.13

rote

0.13

son

0.13

Activations Density 0.030%

terms related to numerical analysis and simulations

No Comments

No Known Activations