INDEX

Explanations

non-standard characters or symbols that represent various concepts or entities in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

utow

-0.18

quist

-0.15

/MPL

-0.14

á»ĭnh

-0.14

loha

-0.14

Wr

-0.14

akra

-0.14

etes

-0.14

.fd

-0.14

ODY

-0.14

POSITIVE LOGITS

 Network

0.21

 network

0.21

SN

0.20

Network

0.18

san

0.17

SN

0.16

network

0.16

 bank

0.16

osen

0.15

sa

0.15

Activations Density 0.009%

non-standard characters or symbols that represent various concepts or entities in a text

No Comments

No Known Activations