INDEX

Explanations

code constructs related to class and object definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

/or

-0.19

phans

-0.17

eger

-0.15

afe

-0.15

aten

-0.15

AEA

-0.15

reuse

-0.15

ular

-0.14

axies

-0.14

plier

-0.14

POSITIVE LOGITS

ture

0.15

sert

0.15

Kum

0.14

soever

0.14

ëĳĲ

0.14

ãģĺ

0.13

ÙĪØ§Ø±Ùĩ

0.13

amento

0.13

../../../

0.13

rig

0.13

Activations Density 0.009%

code constructs related to class and object definitions

No Comments

No Known Activations