INDEX

Explanations

references to document identifiers, typically associated with academic papers or articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

oval

-0.16

inel

-0.15

iren

-0.15

ç

-0.14

iglia

-0.14

 Cres

-0.13

 Blasio

-0.13

pty

-0.13

pray

-0.13

ÙĪÙĨÙĩ

-0.13

POSITIVE LOGITS

ityEngine

0.16

èĥ¸

0.14

 CultureInfo

0.14

anca

0.14

.guid

0.14

EventListener

0.13

RIES

0.13

Bush

0.13

tah

0.13

.getDefault

0.13

Activations Density 0.013%

references to document identifiers, typically associated with academic papers or articles

No Comments

No Known Activations