INDEX

Explanations

references to reflection and nostalgia

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

enuity

-0.16

 láº§n

-0.15

deen

-0.14

 Cousins

-0.14

UPPORT

-0.14

 belie

-0.13

erox

-0.13

.exp

-0.13

uali

-0.13

POSITIVE LOGITS

ister

0.19

ISTER

0.16

Ä±rak

0.15

nels

0.15

DataProvider

0.15

jabi

0.15

DataService

0.14

.TextAlignment

0.14

PLE

0.14

\CMS

0.14

Activations Density 0.045%

references to reflection and nostalgia

No Comments

No Known Activations