INDEX

Explanations

terms related to negative or adverse effects and outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

olicit

-0.17

endon

-0.16

ahu

-0.15

scribe

-0.15

iyat

-0.15

oplast

-0.14

azo

-0.14

ãĥ³ãĤ°

-0.14

eno

-0.14

ickness

-0.14

POSITIVE LOGITS

 consequences

0.22

/null

0.21

 effects

0.21

ities

0.18

 aspects

0.18

 reaction

0.18

 reactions

0.18

 publicity

0.17

 consequence

0.17

 experiences

0.17

Activations Density 0.028%

terms related to negative or adverse effects and outcomes

No Comments

No Known Activations