INDEX

Explanations

articles focusing on quality or condition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

usz

-0.16

aes

-0.15

ONGL

-0.14

 Ð½ÐµÐ²

-0.14

ãģŃ

-0.14

OND

-0.14

hle

-0.13

 mÃŃsta

-0.13

YLES

-0.13

esian

-0.13

POSITIVE LOGITS

 revelation

0.19

 concern

0.18

hit

0.18

 blessing

0.17

 necessity

0.17

 inspiration

0.17

 must

0.16

cin

0.16

 asset

0.15

 reflection

0.15

Activations Density 0.181%

articles focusing on quality or condition

No Comments

No Known Activations