INDEX

Explanations

instances of emotional interactions and responses among characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

anj

-0.15

oking

-0.15

.mybatisplus

-0.15

separator

-0.14

itary

-0.14

iang

-0.14

ogui

-0.14

ym

-0.14

ycz

-0.14

voke

-0.14

POSITIVE LOGITS

 then

0.19

 reply

0.18

 Reply

0.17

 accordingly

0.17

 response

0.17

 responds

0.17

reply

0.16

-reply

0.16

 respond

0.16

 responded

0.16

Activations Density 0.374%

instances of emotional interactions and responses among characters

No Comments

No Known Activations