INDEX

Explanations

references to time durations and periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

Enlarge

-0.15

dek

-0.15

$MESS

-0.15

vox

-0.15

oro

-0.15

aises

-0.15

endar

-0.14

à¸ļà¸ģ

-0.14

 Epic

-0.14

lip

-0.14

POSITIVE LOGITS

 amount

0.23

 amounts

0.19

 time

0.19

 period

0.19

 periods

0.18

amount

0.18

 Ð²ÑĢÐµÐ¼ÐµÐ½Ð¸

0.18

Amount

0.17

 architekt

0.17

0.16

Activations Density 0.101%

references to time durations and periods

No Comments

No Known Activations