INDEX

Explanations

phrases indicating physical presence or proximity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ix

-0.18

 éĤ

-0.16

ancia

-0.15

adius

-0.15

esan

-0.15

phere

-0.15

ortex

-0.15

ascimento

-0.14

ancias

-0.14

imate

-0.14

POSITIVE LOGITS

 cameras

0.20

-camera

0.20

 camera

0.18

ÅĤu

0.17

į°ìĿ´

0.16

AYER

0.16

ultz

0.16

 witnesses

0.15

-runner

0.14

uria

0.14

Activations Density 0.027%

phrases indicating physical presence or proximity

No Comments

No Known Activations