INDEX

Explanations

phrases indicating investigation and inquiry into information or events

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

alink

-0.19

 Tube

-0.16

Tube

-0.15

 addCriterion

-0.14

amax

-0.14

 Kobe

-0.14

 Recomm

-0.14

 tube

-0.13

Ã

-0.13

 bump

-0.13

POSITIVE LOGITS

 study

0.23

 look

0.23

 examination

0.22

 examine

0.20

 comparison

0.20

mlin

0.20

çľĭçľĭ

0.19

 compare

0.19

 investigation

0.19

 check

0.18

Activations Density 0.298%

phrases indicating investigation and inquiry into information or events

No Comments

No Known Activations