INDEX

Explanations

references to prestigious awards or prizes

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

oller

-0.17

_kb

-0.16

uger

-0.15

hait

-0.15

zug

-0.15

.misc

-0.15

ÃŃcia

-0.15

ering

-0.14

 Ð¶Ðµ

-0.14

Sit

-0.14

POSITIVE LOGITS

 onBind

0.15

uchs

0.15

ansson

0.14

çº§

0.14

ByExample

0.14

-bot

0.14

Bot

0.14

áº¯ng

0.14

 Destiny

0.13

rex

0.13

Activations Density 0.003%

references to prestigious awards or prizes

No Comments

No Known Activations