INDEX

Explanations

references to writing and composition in educational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

roll

-0.16

aro

-0.15

 addCriterion

-0.15

hill

-0.15

kol

-0.15

queda

-0.15

phinx

-0.15

CTest

-0.15

adar

-0.14

 Theft

-0.14

POSITIVE LOGITS

ovah

0.15

iative

0.14

_iters

0.14

ysl

0.14

 CascadeType

0.14

ersiz

0.14

ITH

0.14

ith

0.14

Alv

0.14

ocop

0.14

Activations Density 0.005%

references to writing and composition in educational contexts

No Comments

No Known Activations