INDEX

Explanations

keywords associated with serious incidents and consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ifold

-0.17

artic

-0.15

oux

-0.14

 artic

-0.14

bia

-0.14

 posled

-0.14

ovu

-0.14

esser

-0.14

ilingual

-0.14

 alternate

-0.14

POSITIVE LOGITS

StringValue

0.16

vise

0.14

ISOString

0.14

ivec

0.14

urret

0.14

afs

0.14

reeze

0.14

rys

0.14

afari

0.13

AAP

0.13

Activations Density 0.011%

keywords associated with serious incidents and consequences

No Comments

No Known Activations