INDEX

Explanations

concepts related to transformation and generation of data or goods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

acco

-0.14

ustr

-0.14

#SBATCH

-0.14

arda

-0.13

allas

-0.13

enci

-0.12

aga

-0.12

ãĥ¬ãĥ³

-0.12

iga

-0.12

toi

-0.12

POSITIVE LOGITS

 from

0.58

from

0.51

 FROM

0.46

_from

0.44

 From

0.44

.from

0.42

 based

0.42

-from

0.41

	from

0.41

à¸Īà¸²à¸ģ

0.40

Activations Density 0.198%

concepts related to transformation and generation of data or goods

No Comments

No Known Activations