INDEX

Explanations

information related to historical figures and their roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

Î¿Î»

-0.15

calar

-0.15

erge

-0.15

ocratic

-0.15

 addCriterion

-0.14

 downt

-0.14

oden

-0.14

imer

-0.14

Ä±mÄ±zda

-0.14

hatt

-0.14

POSITIVE LOGITS

ige

0.19

stell

0.17

 Initi

0.17

 borderTop

0.17

Che

0.16

idge

0.16

quier

0.15

áº¡

0.14

 Refer

0.14

lang

0.14

Activations Density 0.028%

information related to historical figures and their roles

No Comments

No Known Activations