INDEX

Explanations

quantifiable measurements or counts in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

gne

-0.15

.AddComponent

-0.15

adio

-0.15

abet

-0.15

zens

-0.14

gend

-0.14

å½¦

-0.14

æĹıèĩªæ²»

-0.14

\Doctrine

-0.14

isko

-0.14

POSITIVE LOGITS

 syll

0.17

imos

0.16

 Whit

0.15

uckle

0.14

 Stephan

0.14

_far

0.14

erial

0.14

 retries

0.14

 affairs

0.14

Activations Density 0.280%

quantifiable measurements or counts in various contexts

No Comments

No Known Activations