INDEX

Explanations

references to mentoring and mentorship programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

kie

-0.18

ely

-0.16

onica

-0.16

lub

-0.14

Ð²Ð¸ÑĤ

-0.14

âĶģ

-0.14

abeth

-0.14

/page

-0.14

ÐµÑĢÐ²

-0.13

ÙĪØ¯ÛĮ

-0.13

POSITIVE LOGITS

ship

0.28

ships

0.18

ific

0.18

SHIP

0.16

ë§ģ

0.15

apore

0.15

rible

0.15

ucci

0.14

æĿĲ

0.14

inent

0.14

Activations Density 0.026%

references to mentoring and mentorship programs

No Comments

No Known Activations