INDEX

Explanations

references to clarity, consistency, and structured information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

zik

-0.19

 Vacc

-0.16

 hearing

-0.15

iste

-0.15

 accord

-0.15

led

-0.14

 Sadd

-0.14

 touch

-0.14

LTS

-0.13

itz

-0.13

POSITIVE LOGITS

ulumi

0.15

-clear

0.14

.scalablytyped

0.14

usra

0.14

ynchronized

0.14

ournals

0.14

tero

0.14

:both

0.14

xes

0.14

erson

0.14

Activations Density 0.164%

references to clarity, consistency, and structured information

No Comments

No Known Activations