INDEX

Explanations

expressions related to warranties and liability disclaimers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

issy

-0.18

mon

-0.14

TRACE

-0.14

vÃ¡l

-0.14

til

-0.14

 tilt

-0.13

 dÃ¢n

-0.13

/calendar

-0.13

anner

-0.13

POSITIVE LOGITS

hq

0.15

ecial

0.15

_ALLOW

0.15

quina

0.14

 ä¿Ŀ

0.14

Ã©rc

0.14

']->

0.14

hai

0.13

-labelledby

0.13

Activations Density 0.005%

expressions related to warranties and liability disclaimers

No Comments

No Known Activations