INDEX

Explanations

concepts related to governance and oversight

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

{@

-0.17

erap

-0.14

ullah

-0.14

rente

-0.14

ektor

-0.14

ertos

-0.14

&type

-0.14

rocket

-0.14

Ã¼Ã§

-0.14

erts

-0.13

POSITIVE LOGITS

 Pill

0.15

ecast

0.15

rier

0.14

 Pest

0.14

 Mori

0.14

 pest

0.13

conde

0.13

 Core

0.13

 pill

0.13

reme

0.13

Activations Density 0.078%

concepts related to governance and oversight

No Comments

No Known Activations