INDEX

Explanations

occurrences of the word "Met" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ederland

-0.17

acia

-0.16

verty

-0.16

Î·ÏĥÎ·

-0.16

edList

-0.16

erland

-0.16

ÄŁinin

-0.15

 Alban

-0.15

akash

-0.15

isty

-0.15

POSITIVE LOGITS

ropolitan

0.28

ropolis

0.26

tle

0.24

ting

0.22

/met

0.20

abolic

0.20

ropol

0.20

ters

0.19

Met

0.18

airie

0.18

Activations Density 0.024%

occurrences of the word "Met" and its variations in different contexts

No Comments

No Known Activations