INDEX

Explanations

words and phrases related to actions and states of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ADF

-0.15

aceutical

-0.15

eref

-0.15

ationale

-0.15

opher

-0.15

kke

-0.15

emez

-0.14

 minWidth

-0.13

utan

-0.13

çŃĭ

-0.13

POSITIVE LOGITS

gh

0.15

plat

0.14

rame

0.14

 planta

0.13

chimp

0.13

ÃŃo

0.13

³

0.13

relude

0.13

ìĤ°ìĹħ

0.13

pheric

0.13

Activations Density 0.066%

words and phrases related to actions and states of being

No Comments

No Known Activations