INDEX

Explanations

words that indicate support or endorsement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

COME

-0.17

 gaining

-0.15

Ã¡d

-0.14

 Ð¿Ð¾Ð»ÑĥÑĩÐµÐ½Ð¸Ñı

-0.14

imps

-0.14

finding

-0.14

åħ¥åı£

-0.14

POSITIVE LOGITS

 being

0.30

 having

0.23

 Being

0.22

being

0.22

how

0.22

Being

0.20

 everything

0.19

 their

0.19

 essere

0.18

 what

0.18

Activations Density 0.098%

words that indicate support or endorsement

No Comments

No Known Activations