INDEX

Explanations

references to time intervals and durations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

icens

-0.15

kiye

-0.15

 yearly

-0.15

-0.14

ivery

-0.14

EC

-0.14

 annual

-0.14

iggs

-0.14

å¾Ĵ

-0.14

 isolated

-0.14

POSITIVE LOGITS

 throughout

0.23

 until

0.20

until

0.20

_until

0.19

 Throughout

0.18

 hasta

0.17

Throughout

0.16

 jusqu

0.16

 Until

0.16

Until

0.15

Activations Density 0.225%

references to time intervals and durations

No Comments

No Known Activations