INDEX

Explanations

references to government ministries and their functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

aku

-0.18

pais

-0.15

gang

-0.15

mong

-0.14

ExecutionContext

-0.14

âħ

-0.14

adla

-0.14

junction

-0.14

oman

-0.14

 Occupation

-0.14

POSITIVE LOGITS

 Affairs

0.23

 affairs

0.19

owi

0.16

esser

0.16

ÑĦÑĸÐº

0.15

Culture

0.15

vig

0.15

çļĦäºĭ

0.14

uptools

0.14

ÄĽk

0.14

Activations Density 0.061%

references to government ministries and their functions

No Comments

No Known Activations

references to government ministries and their functions

No Comments

No Known Activations