INDEX

Explanations

terms related to impact and scrutiny, particularly in contexts of danger and control

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

isation

-0.29

ization

-0.23

itation

-0.19

ication

-0.18

isations

-0.18

IZATION

-0.17

ation

-0.17

ATION

-0.17

iliation

-0.17

igation

-0.16

POSITIVE LOGITS

undry

0.15

aset

0.15

atest

0.15

esda

0.14

Ã¤l

0.14

atically

0.14

:invoke

0.14

ewhat

0.14

antly

0.14

nowled

0.14

Activations Density 0.116%

terms related to impact and scrutiny, particularly in contexts of danger and control

No Comments

No Known Activations