INDEX

Explanations

emotional expressions and responses in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

"],"

-0.12

ãģ¯ãģļ

-0.12

.scalablytyped

-0.12

(*)(

-0.12

eliac

-0.12

//{{

-0.11

ĮĴ

-0.11

 ngÆ°á»£c

-0.11

ÑĤÐ°Ð¿

-0.11

.initializeApp

-0.11

POSITIVE LOGITS

 then

1.54

then

1.30

 Then

1.19

 THEN

1.18

Then

1.16

THEN

1.02

_then

1.00

	then

0.97

 entonces

0.96

.then

0.91

Activations Density 1.963%

emotional expressions and responses in various contexts

No Comments

No Known Activations