INDEX

Explanations

references to years or time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 occasionally

-0.27

 occasional

-0.23

 Occasionally

-0.22

 periodically

-0.18

Occ

-0.17

åģ¶

-0.16

udes

-0.16

 occas

-0.15

 ocas

-0.15

 sometimes

-0.15

POSITIVE LOGITS

latest

0.21

 latest

0.18

æľĢæĸ°

0.16

obi

0.16

iddy

0.16

Latest

0.15

alte

0.15

.latest

0.15

ernen

0.14

 initData

0.14

Activations Density 0.054%

references to years or time periods

No Comments

No Known Activations