INDEX

Explanations

references to events or gatherings

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

-0.15

lia

-0.15

ark

-0.14

noÅĽci

-0.14

.ov

-0.14

CreatedBy

-0.13

ddb

-0.13

OPY

-0.13

undle

-0.13

POSITIVE LOGITS

 held

0.56

held

0.47

 Held

0.42

-held

0.40

 hosted

0.29

 conducted

0.29

 Ø¨Ø±Ú¯Ø²Ø§Ø±

0.26

 diá»ħn

0.25

 happening

0.24

 occurs

0.24

Activations Density 0.117%

references to events or gatherings

No Known Activations