INDEX

Explanations

mentions of COVID-19 related statistics and terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

tsy

-0.15

ç¢

-0.14

inous

-0.14

rance

-0.13

orts

-0.13

hash

-0.13

áº»

-0.13

mts

-0.13

ÑĢÐ°Ñĩ

-0.13

ÙĴØ³

-0.13

POSITIVE LOGITS

ï¸ı

0.16

 Bloss

0.16

PIO

0.15

ollen

0.14

esModule

0.14

PIP

0.14

-related

0.14

ongan

0.14

egov

0.14

Activations Density 0.008%

mentions of COVID-19 related statistics and terms

No Comments

No Known Activations