INDEX

Explanations

expressions related to moral implications and ethical considerations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

isable

-0.18

ization

-0.17

ized

-0.16

apolis

-0.16

/or

-0.15

à¸Ļ

-0.15

izable

-0.15

isation

-0.15

raph

-0.14

ãĥ§

-0.14

POSITIVE LOGITS

ìĦľëĬĶ

0.25

entimes

0.19

ings

0.18

lessly

0.18

ments

0.18

à¸£

0.17

INUX

0.17

ãģ¹ãģį

0.16

INGS

0.15

forth

0.15

Activations Density 0.524%

expressions related to moral implications and ethical considerations

No Comments

No Known Activations