INDEX

Explanations

mathematical expressions and terms related to statistical laws and probabilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ufac

-0.15

arkin

-0.14

agna

-0.14

rium

-0.14

Nova

-0.14

<typeof

-0.13

dff

-0.13

engin

-0.13

 unfavorable

-0.13

POSITIVE LOGITS

Pit

0.15

aises

0.15

 Mall

0.15

 Primitive

0.15

thr

0.14

primitive

0.14

+xml

0.14

Ø¤

0.13

Dix

0.13

 Comput

0.13

Activations Density 0.003%

mathematical expressions and terms related to statistical laws and probabilities

No Comments

No Known Activations