INDEX

Explanations

descriptions related to flags and medals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

hiba

-0.15

bler

-0.14

ousse

-0.14

Trap

-0.14

 Falls

-0.14

bid

-0.14

bid

-0.14

ç´ł

-0.14

çľī

-0.13

bot

-0.13

POSITIVE LOGITS

 Glory

0.15

ummy

0.15

hana

0.14

áº¡ng

0.14

wers

0.14

aunch

0.14

rich

0.13

uran

0.13

ä»½

0.13

Activations Density 0.015%

descriptions related to flags and medals

No Comments

No Known Activations