INDEX

Explanations

instances of emotional expressions or reactions

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

alers

-0.14

ibbon

-0.14

astes

-0.14

ocr

-0.14

ãĢģãģĿãģĨ

-0.14

assi

-0.14

èįĴ

-0.13

isku

-0.13

èĶµ

-0.13

ahas

-0.13

POSITIVE LOGITS

 someone

0.23

 sire

0.23

 dozens

0.22

 several

0.21

 smoke

0.21

 bunch

0.20

 cars

0.20

 hundreds

0.20

 somebody

0.20

 numerous

0.19

Activations Density 0.736%

instances of emotional expressions or reactions

No Comments

No Known Activations