INDEX

Explanations

expressions that emphasize key observations or opinions about various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

strup

-0.20

Ð°Ð±Ð¾

-0.15

nish

-0.15

ä¹

-0.15

ook

-0.15

Î¯ÏĦ

-0.14

uch

-0.13

PFN

-0.13

 âĢı

-0.13

POSITIVE LOGITS

 thing

0.37

 Thing

0.30

Thing

0.30

thing

0.27

THING

0.21

ãģĵãģ¨ãģ«

0.20

 part

0.19

(thing

0.18

 fact

0.17

 totiÅ¾

0.16

Activations Density 0.108%

expressions that emphasize key observations or opinions about various topics

No Comments

No Known Activations