INDEX

Explanations

phrases that express intentions or desires, particularly those starting with "to" followed by actions or aspirations

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

ivil

-0.15

jk

-0.15

iless

-0.15

 Stern

-0.15

 realise

-0.14

ÏĨÎ¿

-0.14

Ø´ÙĪØ±

-0.13

_refl

-0.13

/kernel

-0.13

erk

-0.13

POSITIVE LOGITS

 hearing

0.22

 hear

0.21

 seeing

0.21

ALAR

0.19

see

0.19

åĲ¬åĪ°

0.18

 hears

0.17

 able

0.17

çľĭåĪ°

0.17

 sees

0.15

Activations Density 0.066%

phrases that express intentions or desires, particularly those starting with "to" followed by actions or aspirations

No Comments

No Known Activations