INDEX

Explanations

concepts relating to emotional responses and processing difficult information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

inta

-0.19

theid

-0.16

emu

-0.16

ÐµÑĤÑĥ

-0.15

bic

-0.15

egl

-0.14

avec

-0.14

dia

-0.14

obi

-0.13

 Padding

-0.13

POSITIVE LOGITS

 retention

0.23

 memor

0.23

 Memor

0.21

 memory

0.19

 assim

0.19

 Memory

0.18

 retaining

0.17

 MEMORY

0.17

 retain

0.17

-memory

0.17

Activations Density 0.181%

concepts relating to emotional responses and processing difficult information

No Comments

No Known Activations