INDEX

Explanations

programming and technical terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 Rocky

-0.17

-webpack

-0.15

oogle

-0.15

Bod

-0.14

 Sebastian

-0.14

iber

-0.14

ç¢º

-0.14

eler

-0.13

 variant

-0.13

POSITIVE LOGITS

 Parse

0.20

InBackground

0.20

ACL

0.19

Parse

0.19

(Parse

0.18

arges

0.17

PF

0.16

PF

0.16

 ParseException

0.16

iteDatabase

0.16

Activations Density 0.001%

programming and technical terminology

No Comments

No Known Activations