INDEX

Explanations

details about relationships and connections among entities or components

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

HING

-0.17

jong

-0.15

hin

-0.14

.fre

-0.14

indre

-0.14

 Kurd

-0.14

åĪĢ

-0.14

ertia

-0.14

estr

-0.13

/AFP

-0.13

POSITIVE LOGITS

esser

0.17

are

0.15

Ð½Ð°Ð½Ð½Ñı

0.14

Porno

0.14

OLS

0.14

 alike

0.14

Assignable

0.14

áº·n

0.13

illez

0.13

à¸±à¸ĩà¸ģ

0.13

Activations Density 0.563%

details about relationships and connections among entities or components

No Comments

No Known Activations