INDEX

Explanations

academic publications and reports related to research and analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ijn

-0.15

.crm

-0.14

á»Ļi

-0.14

val

-0.14

ahn

-0.14

Bik

-0.13

ours

-0.13

val

-0.13

 magn

-0.13

POSITIVE LOGITS

.scalablytyped

0.22

ubl

0.15

stagram

0.15

ãĤĤãĤĬ

0.14

eÄį

0.14

 ModelState

0.14

uable

0.14

pector

0.14

aber

0.14

 tá»§

0.14

Activations Density 0.064%

academic publications and reports related to research and analysis

No Comments

No Known Activations

academic publications and reports related to research and analysis

No Comments

No Known Activations