INDEX

Explanations

numbers and alphanumeric sequences within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

vard

-0.18

icket

-0.18

erval

-0.17

eldon

-0.16

oden

-0.16

icks

-0.15

evin

-0.14

ÑīÐ¸Ð½

-0.14

rome

-0.14

byss

-0.14

POSITIVE LOGITS

0.19

0.17

0.16

eurs

0.15

esktop

0.15

 nowrap

0.15

 Rosenstein

0.14

 Amber

0.14

zy

0.14

hait

0.14

Activations Density 0.034%

numbers and alphanumeric sequences within the text

No Comments

No Known Activations