INDEX

Explanations

words that indicate something is inappropriate or unsuitable

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ky

-0.15

iena

-0.15

jq

-0.14

AZE

-0.14

kl

-0.14

idence

-0.14

tement

-0.14

¬¬

-0.14

amas

-0.13

adece

-0.13

POSITIVE LOGITS

 peak

0.23

peak

0.21

olicited

0.21

ung

0.21

ightly

0.21

ull

0.19

olved

0.19

uitable

0.19

avour

0.19

atisf

0.19

Activations Density 0.005%

words that indicate something is inappropriate or unsuitable

No Comments

No Known Activations

words that indicate something is inappropriate or unsuitable

No Comments

No Known Activations