INDEX

Explanations

expressions of personal experience and emotional reflection

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

 preference

-0.17

 stuff

-0.16

 similarly

-0.16

 Prefer

-0.16

ãĤ§

-0.15

 Enough

-0.15

prefer

-0.15

 likewise

-0.14

.Initialize

-0.14

uka

-0.14

POSITIVE LOGITS

 very

0.33

very

0.28

 bardzo

0.27

Very

0.26

 sehr

0.26

 Very

0.25

 extremely

0.24

éĿŀå¸¸

0.24

 really

0.23

 Ð¾ÑĩÐµÐ½ÑĮ

0.23

Activations Density 0.026%

expressions of personal experience and emotional reflection

No Comments

No Known Activations