INDEX

Explanations

statements indicating uncertainty or differing viewpoints on a subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

amilia

-0.16

uil

-0.14

ere

-0.14

posta

-0.13

llib

-0.13

ascar

-0.13

Äĥng

-0.13

Unexpected

-0.13

Ð»ÐµÐº

-0.13

ori

-0.13

POSITIVE LOGITS

 indications

0.31

 indication

0.27

 evidence

0.27

 signs

0.25

 growing

0.23

 Signs

0.22

 Evidence

0.21

indic

0.19

Evidence

0.19

-growing

0.18

Activations Density 0.087%

statements indicating uncertainty or differing viewpoints on a subject

No Comments

No Known Activations