INDEX

Explanations

informal phrases indicating uncertainty or reluctance

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

anke

-0.16

 èĳ

-0.15

tero

-0.15

mime

-0.15

ecer

-0.15

oningen

-0.14

elah

-0.14

-keys

-0.14

ê°Ī

-0.14

Î¹Î½Î®

-0.14

POSITIVE LOGITS

osi

0.16

ç»ľ

0.15

gÄ±n

0.15

_until

0.14

gi

0.14

oce

0.14

 tomorrow

0.14

å¹²

0.14

aml

0.14

Activations Density 0.171%

informal phrases indicating uncertainty or reluctance

No Comments

No Known Activations