INDEX

Explanations

academic citations and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 post

-0.15

elage

-0.14

èª

-0.14

egas

-0.14

.DataSource

-0.14

awan

-0.14

ocht

-0.14

abin

-0.14

 ransom

-0.14

ex

-0.14

POSITIVE LOGITS

 Google

0.27

Google

0.27

 google

0.22

/google

0.22

.Google

0.21

_google

0.21

 CrossRef

0.20

Cross

0.20

oogle

0.20

google

0.19

Activations Density 0.090%

academic citations and references

No Comments

No Known Activations