INDEX

Explanations

words and phrases related to apologies and expressions of regret

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

reb

-0.16

 Sylv

-0.15

Decorator

-0.14

strike

-0.14

 Horn

-0.14

.experimental

-0.14

la

-0.14

Pis

-0.14

stab

-0.14

rib

-0.13

POSITIVE LOGITS

inkel

0.18

agram

0.16

amas

0.16

uger

0.15

Ã³st

0.15

acman

0.14

imm

0.14

zers

0.14

pery

0.14

ucken

0.14

Activations Density 0.040%

words and phrases related to apologies and expressions of regret

No Comments

No Known Activations