INDEX

Explanations

expressions related to statistical independence and distribution laws

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

quat

-0.16

ican

-0.15

upert

-0.14

quan

-0.14

 works

-0.14

iju

-0.14

Works

-0.14

Ali

-0.14

/spec

-0.13

Vs

-0.13

POSITIVE LOGITS

odate

0.15

TEGER

0.15

oppel

0.15

=-=-=-=-=-=-=-=-

0.14

æİª

0.14

isinde

0.14

 simpler

0.14

phia

0.14

æļ

0.14

Activations Density 0.096%

expressions related to statistical independence and distribution laws

No Comments

No Known Activations