INDEX

Explanations

references to places and notable events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

OutOfBounds

-0.17

ake

-0.15

ertas

-0.15

inou

-0.15

odash

-0.14

sdale

-0.14

bian

-0.14

ville

-0.13

ãĥ¼ãĥ«ãĥī

-0.13

rze

-0.13

POSITIVE LOGITS

istrovstvÃŃ

0.19

zoom

0.17

IALIZ

0.16

 zoom

0.16

Ã±ana

0.15

 Zoom

0.15

Ø²Ùĩ

0.15

 Barcl

0.15

 Detail

0.14

Detail

0.14

Activations Density 0.001%

references to places and notable events

No Comments

No Known Activations