INDEX

Explanations

references to specific countries and their roles or situations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

-0.17

oldt

-0.17

urus

-0.16

arend

-0.15

ATAB

-0.15

æĹĹ

-0.14

alg

-0.14

irth

-0.14

POS

-0.14

InSeconds

-0.14

POSITIVE LOGITS

istrovstvÃŃ

0.18

oves

0.15

Ø±Ø§Øª

0.14

apis

0.14

Cah

0.14

ies

0.14

ippi

0.13

 penn

0.13

ÃŃveis

0.13

criptors

0.13

Activations Density 0.101%

references to specific countries and their roles or situations in various contexts

No Comments

No Known Activations