INDEX

Explanations

structured lists or enumerated items in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

igit

-0.16

 awake

-0.15

abar

-0.15

 Tham

-0.15

eing

-0.15

autor

-0.15

 htons

-0.14

atten

-0.14

YRO

-0.14

 Sink

-0.14

POSITIVE LOGITS

uby

0.14

SocketAddress

0.14

ãĤ¡

0.14

_HP

0.14

 pard

0.13

 Ø°Ùĩ

0.13

ropoda

0.13

PropTypes

0.13

.trip

0.13

ospels

0.13

Activations Density 0.012%

structured lists or enumerated items in a document

No Comments

No Known Activations