INDEX

Explanations

references to reports 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 @ 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

loor

-0.16

/Foundation

-0.16

 Ø¹Ø²

-0.15

ntax

-0.15

ullen

-0.15

 norge

-0.15

rÃ³d

-0.15

CSI

-0.15

InSection

-0.14

ourage

-0.14

POSITIVE LOGITS

0.19

arry

0.18

aj

0.17

oldt

0.16

 Polly

0.15

is

0.14

 borderTop

0.14

fall

0.14

 GeÃ§

0.14

Activations Density 0.078%

references to reports or articles

No Comments

No Known Activations