INDEX

Explanations

phrases indicating potential or hypothetical situations involving "having" or "being."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

now

-0.27

now

-0.26

 lately

-0.20

yet

-0.20

-now

-0.19

 ÑĤÐµÐ¿ÐµÑĢÑĮ

-0.19

 hasn

-0.18

 evidently

-0.18

 apparently

-0.18

 recently

-0.18

POSITIVE LOGITS

 known

0.24

 Known

0.20

 expected

0.20

known

0.19

 easily

0.18

 been

0.18

Known

0.17

 sooner

0.17

asily

0.17

 guessed

0.17

Activations Density 0.079%

phrases indicating potential or hypothetical situations involving "having" or "being."

No Comments

No Known Activations