INDEX

Explanations

documentation comments and code structure in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

bern

-0.15

elpers

-0.15

.Atomic

-0.15

ies

-0.15

pector

-0.15

aken

-0.14

acks

-0.14

aida

-0.14

ÑİÑĤ

-0.14

ubit

-0.14

POSITIVE LOGITS

Ã¼ml

0.16

eo

0.15

à¸¸à¹ī

0.15

Convention

0.15

_sz

0.14

ulum

0.14

kke

0.14

ãĥ³ãĥĶ

0.14

å¼ı

0.13

filt

0.13

Activations Density 0.003%

documentation comments and code structure in programming contexts

No Comments

No Known Activations