INDEX

Explanations

references to gaming and virtual experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

idelberg

-0.19

KER

-0.16

ÙħÙĦ

-0.15

advance

-0.15

orgh

-0.15

peria

-0.14

arb

-0.14

izm

-0.14

^K

-0.14

POSITIVE LOGITS

egan

0.21

zell

0.18

ĴĮ

0.15

 cave

0.14

staking

0.14

çĶº

0.14

 Tradable

0.14

ucceeded

0.14

incerely

0.14

averse

0.13

Activations Density 0.101%

references to gaming and virtual experiences

No Comments

No Known Activations