INDEX

Explanations

mathematical expressions and variables within equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ades

-0.17

whe

-0.16

æ²³

-0.15

ç«ĭãģ¦

-0.15

 Hemisphere

-0.15

ensis

-0.14

 Carr

-0.14

asta

-0.14

oad

-0.14

 Mand

-0.14

POSITIVE LOGITS

(x

0.19

istrovstvÃŃ

0.15

 Lyons

0.15

âķĿ

0.14

BorderStyle

0.14

ç²ī

0.14

à¸§à¸Ķ

0.14

ugins

0.14

 VÅ¡

0.14

kor

0.14

Activations Density 0.195%

mathematical expressions and variables within equations

No Comments

No Known Activations