INDEX

Explanations

terms related to education and teaching methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

zza

-0.14

 grass

-0.14

 spar

-0.14

anye

-0.14

omo

-0.14

 monet

-0.13

 vill

-0.13

 Meer

-0.13

åıİ

-0.13

 Grass

-0.13

POSITIVE LOGITS

æģ

0.17

ped

0.16

 scaffold

0.16

 scaff

0.16

IGHL

0.15

 Scaffold

0.15

<quote

0.15

erde

0.14

ENCIL

0.14

Activations Density 0.030%

terms related to education and teaching methodologies

No Comments

No Known Activations