INDEX

Explanations

mentions of specific news sources and dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ð½Ð¾Ñģ

-0.15

 ÙĨØŃ

-0.15

inous

-0.15

ÐºÐ°Ñģ

-0.14

ÙħØŃ

-0.14

 LGPL

-0.14

Deg

-0.14

Deg

-0.14

åĻ

-0.13

ysz

-0.13

POSITIVE LOGITS

DNA

0.33

dna

0.32

 Times

0.32

PT

0.29

ET

0.28

 TIMES

0.28

HT

0.28

DNA

0.28

 times

0.27

 Mint

0.27

Activations Density 0.039%

mentions of specific news sources and dates

No Comments

No Known Activations