INDEX

Explanations

themes related to recognition, respect, and deserving qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

estro

-0.16

ëĭ´

-0.16

rak

-0.16

UGE

-0.15

foy

-0.15

nici

-0.15

avra

-0.15

anton

-0.15

POSITIVE LOGITS

 deserve

0.77

 deserves

0.70

 deserved

0.64

 deserving

0.61

 merit

0.51

 merits

0.49

 earned

0.49

 warrant

0.44

 Earn

0.43

 entitled

0.42

Activations Density 0.243%

themes related to recognition, respect, and deserving qualities

No Comments

No Known Activations

themes related to recognition, respect, and deserving qualities

No Comments

No Known Activations