INDEX

Explanations

positive and negative sentiments about a hotel experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

.heroku

-0.15

ç¦®

-0.14

ushi

-0.13

tÄĽ

-0.13

gang

-0.13

 tomorrow

-0.13

tility

-0.13

 vintage

-0.13

azine

-0.13

ingham

-0.13

POSITIVE LOGITS

ëĶĶ

0.15

Ø¨Ø³

0.15

íģ

0.14

ëĭ¬

0.14

Driving

0.13

 Staff

0.13

ierge

0.13

osa

0.13

.FontStyle

0.13

.mo

0.13

Activations Density 0.147%

positive and negative sentiments about a hotel experience

No Comments

No Known Activations