INDEX

Explanations

key terms related to essential products and their associated attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

engl

-0.18

 halinde

-0.14

Mine

-0.14

gili

-0.14

uxe

-0.14

-chan

-0.14

bye

-0.14

leyen

-0.13

emale

-0.13

presso

-0.13

POSITIVE LOGITS

 Bris

0.14

DITION

0.14

 exported

0.14

å£«

0.14

YSTEM

0.13

ieties

0.13

Exporter

0.13

Ãµ

0.13

ands

0.13

agem

0.13

Activations Density 0.539%

key terms related to essential products and their associated attributes

No Comments

No Known Activations