INDEX

Explanations

mathematical expressions and relationships, particularly those involving integrals 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 @ 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

ka

-0.17

-0.16

 Scient

-0.15

ulta

-0.15

å¯Ħ

-0.15

-0.14

umber

-0.14

aska

-0.14

Fla

-0.14

_union

-0.14

POSITIVE LOGITS

#ac

0.17

''''

0.17

veau

0.17

ìĿ´ë²Ħ

0.16

ako

0.15

IFY

0.15

abei

0.15

Ð¾Ð»Ð°Ð¹

0.14

attice

0.14

Russ

0.14

Activations Density 0.170%

mathematical expressions and relationships, particularly those involving integrals and equations

No Comments

No Known Activations