INDEX

Explanations

words indicating emotional depth or complexity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

Ð°Ð½Ð¸ÑĨ

-0.17

things

-0.17

ossa

-0.17

 reperc

-0.16

landa

-0.16

 phenomena

-0.16

 atmos

-0.16

 things

-0.15

 kinds

-0.15

 sentiment

-0.14

POSITIVE LOGITS

 efforts

0.26

own

0.23

 travels

0.22

own

0.22

 selves

0.21

 arsenal

0.20

 instincts

0.19

 approach

0.19

 troubles

0.19

 abilities

0.19

Activations Density 0.418%

words indicating emotional depth or complexity

No Comments

No Known Activations