INDEX

Explanations

conjunctions and phrases that indicate relationships or connections between various concepts

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

Negative Logits

ustin

-0.16

Ã§Ãµes

-0.15

ingroup

-0.14

eg

-0.14

iki

-0.14

aroo

-0.14

omain

-0.14

uges

-0.13

blas

-0.13

 ridic

-0.13

POSITIVE LOGITS

AdminController

0.15

ALS

0.15

 glory

0.15

arl

0.14

AMP

0.14

hazi

0.14

pto

0.14

ogui

0.13

·

0.13

 volume

0.13

Activations Density 0.493%

conjunctions and phrases that indicate relationships or connections between various concepts

No Known Activations