INDEX

Explanations

instances of specific known entities and terms related to art and artwork

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 looph

-0.15

 bark

-0.14

fore

-0.14

olvency

-0.14

 Vital

-0.14

dle

-0.14

 deut

-0.14

PIP

-0.14

 Bernstein

-0.13

olon

-0.13

POSITIVE LOGITS

holm

0.16

owitz

0.15

ÙĪÛĮØ³

0.14

xies

0.14

ernes

0.14

ê´

0.14

HWND

0.14

Ð¾Ð¼Ð°

0.13

ogg

0.13

ETCH

0.13

Activations Density 0.039%

instances of specific known entities and terms related to art and artwork

No Comments

No Known Activations