INDEX

Explanations

specific numerical data, identifiers, or significant dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.18

 moments

-0.16

hiba

-0.15

auled

-0.15

 Moments

-0.15

 Stick

-0.14

atta

-0.14

 Ritch

-0.14

ĥ

-0.14

agens

-0.14

POSITIVE LOGITS

Mo

0.21

mo

0.19

Mo

0.17

mo

0.16

ynet

0.16

oya

0.16

_mo

0.16

MO

0.15

á»Ł

0.15

 èĲ

0.15

Activations Density 0.027%

specific numerical data, identifiers, or significant dates

No Comments

No Known Activations