INDEX

Explanations

mathematical symbols and notations related to equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aggi

-0.17

utzer

-0.15

ruc

-0.15

imler

-0.14

ytt

-0.14

kke

-0.13

XObject

-0.13

orris

-0.13

ÑĢÑĥÐ¿Ð¿

-0.13

kop

-0.13

POSITIVE LOGITS

 alike

0.14

 ============================================================================↵

0.14

[s

0.13

har

0.13

overs

0.13

over

0.13

equ

0.13

 Verm

0.13

“

0.13

Activations Density 0.201%

mathematical symbols and notations related to equations

No Comments

No Known Activations