INDEX

Explanations

references to personal belongings and organizational contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

istrovstvÃŃ

-0.17

ernes

-0.15

avigator

-0.15

ÃŃg

-0.15

ugu

-0.14

íĥģ

-0.14

ç®Ģ

-0.14

Ã¨ge

-0.14

loys

-0.14

.PerformLayout

-0.13

POSITIVE LOGITS

 framework

0.17

 frameworks

0.16

à¤Ĥà¤¬

0.16

 confines

0.15

arto

0.14

 ÙĪØ®

0.14

 regards

0.14

ChangeEvent

0.14

Activations Density 0.162%

references to personal belongings and organizational contexts

No Comments

No Known Activations