INDEX

Explanations

mentions of celebrities and notable figures in the context of events or collaborations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Roose

-0.15

-ok

-0.14

 Flynn

-0.14

_trajectory

-0.13

advanced

-0.13

lius

-0.13

izzer

-0.13

 Freel

-0.13

 Gutenberg

-0.13

gard

-0.13

POSITIVE LOGITS

 legend

0.19

strup

0.17

 legends

0.17

 actor

0.17

 actress

0.16

 astronaut

0.16

 lumin

0.16

ex

0.16

odo

0.15

Sir

0.15

Activations Density 0.285%

mentions of celebrities and notable figures in the context of events or collaborations

No Comments

No Known Activations