INDEX

Explanations

expressions related to variations or types of ranges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

regon

-0.18

ILLISECONDS

-0.15

acades

-0.15

aurus

-0.15

rego

-0.15

IndexChanged

-0.15

ingen

-0.14

berman

-0.14

warts

-0.14

reece

-0.14

POSITIVE LOGITS

:NSMakeRange

0.16

Iterable

0.16

bilt

0.15

pire

0.14

YA

0.14

ecast

0.14

filt

0.14

arin

0.14

Gam

0.14

ugg

0.14

Activations Density 0.041%

expressions related to variations or types of ranges

No Comments

No Known Activations