INDEX

Explanations

mathematical operations and expressions in code or logical syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ufe

-0.17

VER

-0.16

alat

-0.16

dera

-0.15

aN

-0.15

ersh

-0.15

/GPL

-0.15

ENS

-0.15

POSITIVE LOGITS

 Margin

0.16

 margin

0.15

ilik

0.15

idla

0.15

ibr

0.14

AllowAnonymous

0.14

umerator

0.14

iber

0.14

å¾Ĺ

0.14

elerik

0.14

Activations Density 0.037%

mathematical operations and expressions in code or logical syntax

No Comments

No Known Activations