INDEX

Explanations

references to educational rankings and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 ç¬

-0.16

Rx

-0.15

ixo

-0.15

kart

-0.15

ABI

-0.15

hower

-0.15

rtc

-0.15

ephir

-0.15

Ãły

-0.14

 Zaman

-0.14

POSITIVE LOGITS

 admissions

0.25

 admission

0.23

 Admission

0.22

 Rankings

0.20

 admit

0.20

 admitting

0.18

QS

0.17

 Ranking

0.17

 admitted

0.17

 ranking

0.17

Activations Density 0.175%

references to educational rankings and statistics

No Comments

No Known Activations