INDEX

Explanations

names and titles related to personal identity and profession

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

cop

-0.16

 Licensing

-0.14

Ð»Ð¸Ðº

-0.14

iphy

-0.14

ione

-0.14

annon

-0.13

lab

-0.13

annie

-0.13

POSITIVE LOGITS

Disposition

0.17

esson

0.16

ama

0.16

 currently

0.15

ertiary

0.15

 born

0.14

 Currently

0.14

uraa

0.14

ertainment

0.14

Trap

0.13

Activations Density 0.207%

names and titles related to personal identity and profession

No Comments

No Known Activations