INDEX

Explanations

equations and mathematical notation

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

onas

-0.16

amam

-0.15

 Bender

-0.14

Inject

-0.14

SYS

-0.13

 Gund

-0.13

localized

-0.13

eman

-0.13

-flat

-0.13

POSITIVE LOGITS

ILI

0.14

issing

0.14

empre

0.14

Ãªu

0.14

Ĵáŀ

0.14

egasus

0.14

phalt

0.13

apos

0.13

ifes

0.13

Activations Density 0.607%

equations and mathematical notation

No Comments

No Known Activations