INDEX

Explanations

phrases indicating contributions or effects related to actions or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

lac

-0.17

urger

-0.15

orf

-0.15

osc

-0.14

ansom

-0.14

.INSTANCE

-0.14

 arity

-0.14

.chomp

-0.13

éĤ£æł·

-0.13

aks

-0.13

POSITIVE LOGITS

 towards

0.29

 toward

0.29

 directly

0.24

Towards

0.21

 Towards

0.20

 significant

0.19

Tow

0.16

 indirectly

0.16

Ã¦k

0.16

 factors

0.15

Activations Density 0.016%

phrases indicating contributions or effects related to actions or situations

No Comments

No Known Activations