INDEX

Explanations

key entities and events in narratives and discussions related to governance and organizational aspects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

asily

-0.16

tml

-0.14

irtual

-0.14

asÄ±yla

-0.13

-Ð·Ð°

-0.13

ensibly

-0.13

 Truy

-0.13

icamente

-0.12

actly

-0.12

atabases

-0.12

POSITIVE LOGITS

liest

0.27

iest

0.26

 itself

0.25

aviest

0.24

osphere

0.19

niest

0.18

iverse

0.18

quirer

0.16

 Ø§ÙĦØ¬Ø¯ÙĬØ¯

0.16

 stesso

0.15

Activations Density 1.870%

key entities and events in narratives and discussions related to governance and organizational aspects

No Comments

No Known Activations