INDEX

Explanations

phrases related to acknowledgment and recognition of deserving individuals or professions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ollah

-0.17

raki

-0.17

nici

-0.16

rak

-0.16

ëĭ´

-0.16

lius

-0.15

egov

-0.15

ëĤľ

-0.14

WithURL

-0.14

ello

-0.14

POSITIVE LOGITS

 deserve

0.80

 deserves

0.72

 deserved

0.66

 deserving

0.62

 merit

0.55

 merits

0.52

 earned

0.51

 warrant

0.49

 warrants

0.47

 Earn

0.45

Activations Density 0.261%

phrases related to acknowledgment and recognition of deserving individuals or professions

No Comments

No Known Activations