INDEX

Explanations

mathematical symbols and expressions in equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

inf

-0.18

erb

-0.17

alan

-0.15

-0.14

inf

-0.14

oe

-0.14

arez

-0.14

ulado

-0.14

acl

-0.14

ypy

-0.14

POSITIVE LOGITS

instein

0.17

OOT

0.15

ìŀ¥ìĿĦ

0.15

ools

0.15

 Devin

0.14

.appendTo

0.14

Jim

0.14

âĢ«

0.14

elia

0.13

career

0.13

Activations Density 0.315%

mathematical symbols and expressions in equations

No Comments

No Known Activations