INDEX

Explanations

references to films and literature, particularly in academic or critical contexts

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

.tc

-0.16

vvm

-0.15

acement

-0.14

Ð¼Ð¾ÑĢ

-0.13

 Busy

-0.13

-Out

-0.13

ä»ģ

-0.13

asso

-0.13

licht

-0.13

ÙĴÙĦ

-0.13

POSITIVE LOGITS

 autobi

0.18

ency

0.16

 realized

0.16

ÏĦÎ¿Î³ÏģÎ±ÏĨ

0.16

 centr

0.16

 firm

0.15

 exhaust

0.15

iku

0.15

 dedi

0.15

firm

0.14

Activations Density 0.061%

references to films and literature, particularly in academic or critical contexts

No Comments

No Known Activations