INDEX

Explanations

titles and roles related to leadership and authorship

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 Roses

-0.16

Aspect

-0.15

ÑīÐ¸Ð½

-0.15

ÐµÑĤÑĮ

-0.15

 cellForRowAt

-0.14

 Aspect

-0.14

tain

-0.14

hog

-0.14

arsing

-0.14

istrovstvÃŃ

-0.14

POSITIVE LOGITS

anden

0.18

oldem

0.15

 Ð·Ð°Ð²Ð¸

0.15

 WithEvents

0.14

ÑıÑĩ

0.14

ebek

0.14

 bgcolor

0.14

ACHI

0.13

Activations Density 0.082%

titles and roles related to leadership and authorship

No Comments

No Known Activations