INDEX

Explanations

phrases indicating expertise or specialization in various fields

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

auc

-0.15

usercontent

-0.14

acon

-0.13

laus

-0.13

aires

-0.13

handlers

-0.13

ofilm

-0.13

PerPixel

-0.13

.hwp

-0.13

POSITIVE LOGITS

 emphasis

0.56

 particular

0.51

emphasis

0.44

 focus

0.44

phasis

0.38

 emphasize

0.38

Em

0.37

focus

0.36

 accent

0.36

 special

0.36

Activations Density 0.094%

phrases indicating expertise or specialization in various fields

No Comments

No Known Activations