INDEX

Explanations

arrow functions in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

odore

-0.20

asar

-0.14

Äĥ

-0.14

@nate

-0.14

astos

-0.14

acz

-0.14

ĵåĲį

-0.14

aires

-0.14

amente

-0.13

nie

-0.13

POSITIVE LOGITS

 {↵

0.26

 {↵↵

0.21

{//

0.19

 {č↵

0.18

{↵

0.17

 {↵↵↵

0.16

erin

0.16

oval

0.16

{//

0.16

{č↵

0.15

Activations Density 0.032%

arrow functions in programming

No Comments

No Known Activations