INDEX

Explanations

mathematical or scientific notation, particularly involving symbols and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

lab

-0.15

_PIPE

-0.15

åĪĩãĤĬ

-0.15

ilt

-0.14

íĹ¤

-0.14

ght

-0.14

ey

-0.14

ogie

-0.14

-0.13

.Payload

-0.13

POSITIVE LOGITS

enz

0.15

Î¼ÏĮ

0.15

uhl

0.15

uhn

0.14

rado

0.14

block

0.14

åŀ

0.14

alog

0.14

REN

0.14

 Gardner

0.14

Activations Density 0.069%

mathematical or scientific notation, particularly involving symbols and equations

No Comments

No Known Activations