INDEX

Explanations

phrases related to statistical data and comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Richt

-0.15

ÐĲÑĢÑħÑĸÐ²

-0.15

illard

-0.14

eni

-0.14

witch

-0.14

otime

-0.14

ipl

-0.14

 Erotik

-0.14

gov

-0.13

leta

-0.13

POSITIVE LOGITS

 more

0.21

 higher

0.20

 fewer

0.18

 greater

0.18

estone

0.17

elow

0.16

 much

0.15

 larger

0.15

 wiÄĻcej

0.15

 better

0.15

Activations Density 0.250%

phrases related to statistical data and comparisons

No Comments

No Known Activations