INDEX

Explanations

interrogative phrases and questions related to personal experiences and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Have

-0.17

chte

-0.16

 certainly

-0.15

inel

-0.14

Have

-0.14

 HAVE

-0.14

atura

-0.14

paging

-0.14

 demanded

-0.14

 possess

-0.14

POSITIVE LOGITS

 fare

0.27

 fares

0.25

 Fare

0.23

 cope

0.22

 handles

0.22

 react

0.20

 Handles

0.20

 differs

0.20

 stack

0.19

 dealt

0.19

Activations Density 0.095%

interrogative phrases and questions related to personal experiences and actions

No Comments

No Known Activations