INDEX

Explanations

references to user accounts, trust issues, and credential management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Cust

-0.16

pic

-0.15

 Pare

-0.15

ãĥ³ãĥĶ

-0.15

 Hers

-0.15

Lon

-0.14

 Huffman

-0.14

lotte

-0.14

aign

-0.14

 "(\<

-0.14

POSITIVE LOGITS

ker

0.31

Ker

0.30

ker

0.24

 ticket

0.24

KER

0.24

-ticket

0.23

 Ticket

0.23

 tickets

0.22

beros

0.22

ticket

0.22

Activations Density 0.014%

references to user accounts, trust issues, and credential management

No Comments

No Known Activations