INDEX

Explanations

geographic locations and institutions related to research or academia

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 hardware

-0.15

fÃ©

-0.15

agu

-0.14

upe

-0.14

 pare

-0.14

hn

-0.14

len

-0.14

 context

-0.14

hua

-0.13

Fet

-0.13

POSITIVE LOGITS

ê¸ī

0.15

IMA

0.14

ModelIndex

0.14

frauen

0.14

fol

0.14

 ÙħÙĤØ¯

0.14

emet

0.14

inals

0.14

uitka

0.14

rames

0.14

Activations Density 0.041%

geographic locations and institutions related to research or academia

No Comments

No Known Activations