INDEX

Explanations

various options and issues within discussions or propositions

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

FormatException

-0.14

ugin

-0.14

omi

-0.14

chalk

-0.14

åŁ¹

-0.14

ethe

-0.14

noop

-0.14

WX

-0.14

toast

-0.13

 çĤ

-0.13

POSITIVE LOGITS

erap

0.15

ulin

0.15

Ø¨ÙĪØ±

0.15

Cru

0.15

bor

0.14

idir

0.14

asse

0.14

 Moor

0.13

 interval

0.13

 ward

0.13

Activations Density 0.093%

various options and issues within discussions or propositions

No Comments

No Known Activations