INDEX

Explanations

mathematical symbols and expressions related to norms and inequalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 Verm

-0.15

emento

-0.15

ault

-0.15

ati

-0.15

é¨

-0.14

bur

-0.14

gado

-0.14

ÑıÐµÐ¼

-0.14

rible

-0.14

å¢ĥ

-0.14

POSITIVE LOGITS

IT

0.16

ardo

0.16

atro

0.15

ordova

0.14

eer

0.14

ked

0.13

gang

0.13

_growth

0.13

ritic

0.13

osti

0.13

Activations Density 0.039%

mathematical symbols and expressions related to norms and inequalities

No Comments

No Known Activations