INDEX

Explanations

references to indexing and related mathematical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

å¹ķ

-0.20

jev

-0.17

isans

-0.16

angs

-0.16

liness

-0.16

èĤ²

-0.16

tery

-0.15

_inds

-0.15

APSHOT

-0.15

POSITIVE LOGITS

ation

0.35

(es

0.27

OutOfBoundsException

0.27

ical

0.26

 finger

0.24

hibit

0.22

ing

0.22

es

0.21

ional

0.21

OutOfRangeException

0.21

Activations Density 0.044%

references to indexing and related mathematical concepts

No Comments

No Known Activations