INDEX

Explanations

keywords related to significant events or entities in political and historical contexts

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

uve

-0.16

 Platt

-0.15

ughter

-0.15

der

-0.14

 latency

-0.14

æļ®

-0.14

.Framework

-0.14

ino

-0.14

 Ð¿Ð¾ÑĪ

-0.13

POSITIVE LOGITS

 Artem

0.16

Ã©gor

0.16

å£«

0.16

Ã¼stÃ¼

0.14

ÏĥÎºÎµ

0.14

Ã¦re

0.14

idel

0.14

_USB

0.14

 derec

0.13

Activations Density 0.121%

keywords related to significant events or entities in political and historical contexts

No Comments

No Known Activations