INDEX

Explanations

occurrences of the word "under."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

rch

-0.15

 underground

-0.14

ãĥªãĤ«

-0.14

sik

-0.14

anford

-0.14

orgot

-0.14

ekler

-0.13

ataire

-0.13

KI

-0.13

ä¸ĬãģĮ

-0.13

POSITIVE LOGITS

neath

0.32

lined

0.31

lining

0.31

whel

0.27

lying

0.26

 ausp

0.25

 pressure

0.25

sea

0.25

pin

0.24

whelming

0.24

Activations Density 0.052%

occurrences of the word "under."

No Comments

No Known Activations