INDEX

Explanations

references to cloud computing services and architectures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

AZY

-0.15

angent

-0.15

ez

-0.15

holm

-0.14

 grind

-0.14

ÑĤÐµÑĢ

-0.13

wear

-0.13

oire

-0.13

lied

-0.13

 Sidebar

-0.13

POSITIVE LOGITS

0.17

IPA

0.14

aska

0.14

hte

0.14

mts

0.14

UBLE

0.14

inka

0.14

rna

0.14

/google

0.14

ulumi

0.14

Activations Density 0.018%

references to cloud computing services and architectures

No Comments

No Known Activations