INDEX

Explanations

instances of ownership and business operations related to specific individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 ÄĮer

-0.17

zew

-0.16

isan

-0.16

aram

-0.15

bourg

-0.14

.lp

-0.14

Accent

-0.14

ottes

-0.14

Î±ÏģÎ¬

-0.14

ARAM

-0.14

POSITIVE LOGITS

 firm

0.23

 partnership

0.21

Mess

0.21

 Partnership

0.20

 firms

0.20

 Mess

0.20

 partnerships

0.20

 Firm

0.19

 agents

0.19

-agent

0.18

Activations Density 0.063%

instances of ownership and business operations related to specific individuals

No Comments

No Known Activations