INDEX

Explanations

date references in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

áº¥p

-0.16

Ð½Ð¾ÑģÑĤÑĮÑİ

-0.14

atÃ³

-0.14

Ð°Ð»Ð¾Ð¼

-0.14

 AssemblyCopyright

-0.14

ÙĦÙī

-0.13

GRE

-0.13

Href

-0.13

åª

-0.13

mall

-0.13

POSITIVE LOGITS

VL

0.17

 tslib

0.16

CellValue

0.15

usi

0.15

BP

0.14

ardon

0.14

bet

0.14

yas

0.14

uden

0.14

ben

0.14

Activations Density 0.029%

date references in the text

No Comments

No Known Activations